Knowledge Distillation with a Precise Teacher and Prediction with Abstention

Xu Yi, Jian Pu, Hui Zhao

Responsive image

Auto-TLDR; Knowledge Distillation using Deep gambler loss and selective classification framework

Slides Poster

Knowledge distillation, which aims to train model under the supervision from another large model (teacher model) to the original model (student model), has achieved remarkable results in supervised learning. However, there are two major problems with existing knowledge distillation methods. One is the teacher's supervision is sometimes misleading, and the other is the student's prediction is not accurate enough. To address the first issue, instead of learning a combination of both teachers and ground truth, we apply knowledge adjustment to correct teachers' supervision using ground truth. For the second problem, we use the selective classification framework to train the student model. In particular, the deep gambler loss is adopted to predict with reservation by explicitly introducing the $(m+1)$-th class. We consider two settings of knowledge distillation: (1) distillation across different network structures ({\it AlexNet, ResNet}), and (2) distillation across networks with different depths ({\it ResNet18, ResNet50}) to evaluate the effectiveness of our method. The experimental results on benchmark datasets (i.e., {\it Fashion-MNIST, SVHN, CIFAR10, CIFAR100}) are reported with higher prediction accuracies and lower coverage errors.

Similar papers

Efficient Online Subclass Knowledge Distillation for Image Classification

Maria Tzelepi, Nikolaos Passalis, Anastasios Tefas

Responsive image

Auto-TLDR; OSKD: Online Subclass Knowledge Distillation

Slides Poster Similar

Deploying state-of-the-art deep learning models on embedded systems dictates certain storage and computation limitations. During the recent few years Knowledge Distillation (KD) has been recognized as a prominent approach to address this issue. That is, KD has been effectively proposed for training fast and compact deep learning models by transferring knowledge from more complex and powerful models. However, knowledge distillation, in its conventional form, involves multiple stages of training, rendering it a computationally and memory demanding procedure. In this paper, a novel single-stage self knowledge distillation method is proposed, namely Online Subclass Knowledge Distillation (OSKD), that aims at revealing the similarities inside classes, improving the performance of any deep neural model in an online manner. Hence, as opposed to existing online distillation methods, we are able to acquire further knowledge from the model itself, without building multiple identical models or using multiple models to teach each other, rendering the OSKD approach more efficient. The experimental evaluation on two datasets validates that the proposed method improves the classification performance.

Distilling Spikes: Knowledge Distillation in Spiking Neural Networks

Ravi Kumar Kushawaha, Saurabh Kumar, Biplab Banerjee, Rajbabu Velmurugan

Responsive image

Auto-TLDR; Knowledge Distillation in Spiking Neural Networks for Image Classification

Slides Poster Similar

Spiking Neural Networks (SNN) are energy-efficient computing architectures that exchange spikes for processing information, unlike classical Artificial Neural Networks (ANN). Due to this, SNNs are better suited for real-life deployments. However, similar to ANNs, SNNs also benefit from deeper architectures to obtain improved performance. Furthermore, like the deep ANNs, the memory, compute and power requirements of SNNs also increase with model size, and model compression becomes a necessity. Knowledge distillation is a model com- pression technique that enables transferring the learning of a large machine learning model to a smaller model with minimal loss in performance. In this paper, we propose techniques for knowledge distillation in spiking neural networks for the task of image classification. We present ways to distill spikes from a larger SNN, also called the teacher network, to a smaller one, also called the student network, while minimally impacting the classification accuracy. We demonstrate the effectiveness of the proposed method with detailed experiments on three standard datasets while proposing novel distillation methodologies and loss functions. We also present a multi-stage knowledge distillation technique for SNNs using an intermediate network to obtain higher performance from the student network. Our approach is expected to open up new avenues for deploying high performing large SNN models on resource-constrained hardware platforms.

Knowledge Distillation Beyond Model Compression

Fahad Sarfraz, Elahe Arani, Bahram Zonooz

Responsive image

Auto-TLDR; Knowledge Distillation from Teacher to Student

Slides Poster Similar

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various techniques have been proposed since the original formulation, which mimics different aspects of the teacher such as the representation space, decision boundary or intra-data relationship. Some methods replace the one way knowledge distillation from a static teacher with collaborative learning between a cohort of students. Despite the recent advances, a clear understanding of where knowledge resides in a deep neural network and optimal method for capturing knowledge from teacher and transferring it to student still remains an open question. In this study we provide an extensive study on 9 different knowledge distillation methods which covers a broad spectrum of approaches to capture and transfer knowledge. We demonstrate the versatility of the KD framework on different datasets and network architectures under varying capacity gaps between the teacher and student. The study provides intuition for the effects of mimicking different aspects of the teacher and derives insights from the performance of the different distillation approaches to guide the the design of more effective KD methods . Furthermore, our study shows the effectiveness of the KD framework in learning efficiently under varying severity levels of label noise and class imbalance, consistently providing significant generalization gains over standard training. We emphasize that the efficacy of KD goes much beyond a model compression technique and should be considered as a general purpose training paradigm which offers more robustness to common challenges in the real-world datasets compared to the standard training procedure.

Stochastic Label Refinery: Toward Better Target Label Distribution

Xi Fang, Jiancheng Yang, Bingbing Ni

Responsive image

Auto-TLDR; Stochastic Label Refinery for Deep Supervised Learning

Slides Poster Similar

This paper proposes a simple yet effective strategy for improving deep supervised learning, named Stochastic Label Refinery (SLR), by refining training labels to more informative labels. When training a neural network, target distributions (or ground-truth) are typically "hard", which means the target label of each category consists of only 0 and 1. However, the fixed "hard" target distributions do not capture association between categories or that between objects. In this study, instead of using the hard target distributions, we iteratively generate "soft" target label distributions for training the neural networks, which leads to better performances. The soft target distributions are obtained via an Expectation-Maximization (EM) iteration, where the "true" target distributions and the learned models are regarded as hidden variables. In E step, the models are optimized to approximate the target distributions on stochastic splits of training data; In M step, the target distributions are updated with predicted pseudo-label on leave-out splits. Extensive experiments on classification and ordinal regression tasks, empirically prove that the refined target distribution consistently leads to considerable performance improvements even applied on competitive baselines. Notably, in DeepDR 2020 Diabetic Retinopathy Grading (DeepDRiD) challenge, our method improves the quadratic weighted kappa on official validation set from 0.8247 to 0.8348 and achieves a state-of-the-art score on online test set. The proposed SLR technique is easy to implement and practically applicable. The code will be open sourced soon.

Feature Fusion for Online Mutual Knowledge Distillation

Jangho Kim, Minsung Hyun, Inseop Chung, Nojun Kwak

Responsive image

Auto-TLDR; Feature Fusion Learning Using Fusion of Sub-Networks

Slides Poster Similar

We propose a learning framework named Feature Fusion Learning (FFL) that efficiently trains a powerful classifier through a fusion module which combines the feature maps generated from parallel neural networks and generates meaningful feature maps. Specifically, we train a number of parallel neural networks as sub-networks, then we combine the feature maps from each sub-network using a fusion module to create a more meaningful feature map. The fused feature map is passed into the fused classifier for overall classification. Unlike existing feature fusion methods, in our framework, an ensemble of sub-network classifiers transfers its knowledge to the fused classifier and then the fused classifier delivers its knowledge back to each sub-network, mutually teaching one another in an online-knowledge distillation manner. This mutually teaching system not only improves the performance of the fused classifier but also obtains performance gain in each sub-network. Moreover, our model is more beneficial than other alternative methods because different types of network can be used for each sub-network. We have performed a variety of experiments on multiple datasets such as CIFAR-10, CIFAR-100 and ImageNet and proved that our method is more effective than other alternative methods in terms of performances of both sub-networks and the fused classifier, and the aspect of generating meaningful feature maps.

Compact CNN Structure Learning by Knowledge Distillation

Waqar Ahmed, Andrea Zunino, Pietro Morerio, Vittorio Murino

Responsive image

Auto-TLDR; Knowledge Distillation for Compressing Deep Convolutional Neural Networks

Slides Poster Similar

The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices. However, existing methods achieve this objective at the cost of a drop in inference accuracy in computer vision tasks. To address such a drawback, we propose a framework that leverages knowledge distillation along with customizable block-wise optimization to learn a lightweight CNN structure while preserving better control over the compression-performance tradeoff. Considering specific resource constraints, e.g., floating-point operations per second (FLOPs) or model-parameters, our method results in a state of the art network compression while being capable of achieving better inference accuracy. In a comprehensive evaluation, we demonstrate that our method is effective, robust, and consistent with results over a variety of network architectures and datasets, at negligible training overhead. In particular, for the already compact network MobileNet_v2, our method offers up to 2x and 5.2x better model compression in terms of FLOPs and model-parameters, respectively, while getting 1.05% better model performance than the baseline network.

Channel Planting for Deep Neural Networks Using Knowledge Distillation

Kakeru Mitsuno, Yuichiro Nomura, Takio Kurita

Responsive image

Auto-TLDR; Incremental Training for Deep Neural Networks with Knowledge Distillation

Slides Poster Similar

In recent years, deeper and wider neural networks have shown excellent performance in computer vision tasks, while their enormous amount of parameters results in increased computational cost and overfitting. Several methods have been proposed to compress the size of the networks without reducing network performance. Network pruning can reduce redundant and unnecessary parameters from a network. Knowledge distillation can transfer the knowledge of deeper and wider networks to smaller networks. The performance of the smaller network obtained by these methods is bounded by the predefined network. Neural architecture search has been proposed, which can search automatically the architecture of the networks to break the structure limitation. Also, there is a dynamic configuration method to train networks incrementally as sub-networks. In this paper, we present a novel incremental training algorithm for deep neural networks called planting. Our planting can search the optimal network architecture with smaller number of parameters for improving the network performance by augmenting channels incrementally to layers of the initial networks while keeping the earlier trained parameters fixed. Also, we propose using the knowledge distillation method for training the channels planted. By transferring the knowledge of deeper and wider networks, we can grow the networks effectively and efficiently. We evaluate the effectiveness of the proposed method on different datasets such as CIFAR-10/100 and STL-10. For the STL-10 dataset, we show that we are able to achieve comparable performance with only 7% parameters compared to the larger network and reduce the overfitting caused by a small amount of the data.

Automatic Student Network Search for Knowledge Distillation

Zhexi Zhang, Wei Zhu, Junchi Yan, Peng Gao, Guotong Xie

Responsive image

Auto-TLDR; NAS-KD: Knowledge Distillation for BERT

Slides Poster Similar

Pre-trained language models (PLMs), such as BERT, have achieved outstanding performance on multiple natural language processing (NLP) tasks. However, such pre-trained models usually contain a huge number of parameters and are computationally expensive. The high resource demand hinders their application on resource-restricted devices like mobile phones. Knowledge distillation (KD) is an effective compression approach, aiming at encouraging a light-weight student network to imitate the teacher network, and accordingly latent knowledge is transferred from the teacher to student. However, the great majority of student networks in previous KD methods are manually designed, normally a subnetwork of the teacher network. Transformer is generally utilized as the student for compressing BERT but still contains masses of parameters. Motivated by this, we propose a novel approach named NAS-KD, which automatically generates an optimal student network using neural architecture search (NAS) to enhance the distillation for BERT. Experiment on 7 classification tasks in NLP domain demonstrates that NAS-KD can substantially reduce the size of BERT without much performance sacrifice.

Local Clustering with Mean Teacher for Semi-Supervised Learning

Zexi Chen, Benjamin Dutton, Bharathkumar Ramachandra, Tianfu Wu, Ranga Raju Vatsavai

Responsive image

Auto-TLDR; Local Clustering for Semi-supervised Learning

Slides Similar

The Mean Teacher (MT) model of Tarvainen and Valpola has shown favorable performance on several semi-supervised benchmark datasets. MT maintains a teacher model's weights as the exponential moving average of a student model's weights and minimizes the divergence between their probability predictions under diverse perturbations of the inputs. However, MT is known to suffer from confirmation bias, that is, reinforcing incorrect teacher model predictions. In this work, we propose a simple yet effective method called Local Clustering (LC) to mitigate the effect of confirmation bias. In MT, each data point is considered independent of other points during training; however, data points are likely to be close to each other in feature space if they share similar features. Motivated by this, we cluster data points locally by minimizing the pairwise distance between neighboring data points in feature space. Combined with a standard classification cross-entropy objective on labeled data points, the misclassified unlabeled data points are pulled towards high-density regions of their correct class with the help of their neighbors, thus improving model performance. We demonstrate on semi-supervised benchmark datasets SVHN and CIFAR-10 that adding our LC loss to MT yields significant improvements compared to MT and performance comparable to the state of the art in semi-supervised learning.

Towards Low-Bit Quantization of Deep Neural Networks with Limited Data

Yong Yuan, Chen Chen, Xiyuan Hu, Silong Peng

Responsive image

Auto-TLDR; Low-Precision Quantization of Deep Neural Networks with Limited Data

Slides Poster Similar

Recent machine learning methods use increasingly large deep neural networks to achieve state-of-the-art results in various tasks. Network quantization can effectively reduce computation and memory costs without modifying network structures, facilitating the deployment of deep neural networks (DNNs) on cloud and edge devices. However, most of the existing methods usually need time-consuming training or fine-tuning and access to the original training dataset that may be unavailable due to privacy or security concerns. In this paper, we present a novel method to achieve low-precision quantization of deep neural networks with limited data. Firstly, to reduce the complexity of per-channel quantization and the degeneration of per-layer quantization, we introduce group-wise quantization which separates the output channels into groups that each group is quantized separately. Secondly, to better distill knowledge from the pre-trained FP32 model with limited data, we introduce a two-stage knowledge distillation method that divides the optimization process into independent optimization stage and joint optimization stage to address the limitation of layer-wise supervision and global supervision. Extensive experiments on ImageNet2012 (ResNet18/50, ShuffleNetV2, and MobileNetV2) demonstrate that the proposed approach can significantly improve the quantization model's accuracy when only a few training samples are available. We further show that the method also extends to other computer vision architectures and tasks such as object detection and semantic segmentation.

Adaptive Noise Injection for Training Stochastic Student Networks from Deterministic Teachers

Yi Xiang Marcus Tan, Yuval Elovici, Alexander Binder

Responsive image

Auto-TLDR; Adaptive Stochastic Networks for Adversarial Attacks

Slides Similar

Adversarial attacks have been a prevalent problem causing misclassification in machine learning models, with stochasticity being a promising direction towards greater robustness. However, stochastic networks frequently underperform compared to deterministic deep networks. In this work, we present a conceptually clear adaptive noise injection mechanism in combination with teacher-initialisation, which adjusts its degree of randomness dynamically through the computation of mini-batch statistics. This mechanism is embedded within a simple framework to obtain stochastic networks from existing deterministic networks. Our experiments show that our method is able to outperform prior baselines under white-box settings, exemplified through CIFAR-10 and CIFAR-100. Following which, we perform in-depth analysis on varying different components of training with our approach on the effects of robustness and accuracy, through the study of the evolution of decision boundary and trend curves of clean accuracy/attack success over differing degrees of stochasticity. We also shed light on the effects of adversarial training on a pre-trained network, through the lens of decision boundaries.

Can Data Placement Be Effective for Neural Networks Classification Tasks? Introducing the Orthogonal Loss

Brais Cancela, Veronica Bolon-Canedo, Amparo Alonso-Betanzos

Responsive image

Auto-TLDR; Spatial Placement for Neural Network Training Loss Functions

Slides Poster Similar

Traditionally, a Neural Network classification training loss function follows the same principle: minimizing the distance between samples that belong to the same class, while maximizing the distance to the other classes. There are no restrictions on the spatial placement of deep features (last layer input). This paper addresses this issue when dealing with Neural Networks, providing a set of loss functions that are able to train a classifier by forcing the deep features to be projected over a predefined orthogonal basis. Experimental results shows that these `data placement' functions can overcome the training accuracy provided by the classic cross-entropy loss function.

Boundary Optimised Samples Training for Detecting Out-Of-Distribution Images

Luca Marson, Vladimir Li, Atsuto Maki

Responsive image

Auto-TLDR; Boundary Optimised Samples for Out-of-Distribution Input Detection in Deep Convolutional Networks

Slides Poster Similar

This paper presents a new approach to the problem of detecting out-of-distribution (OOD) inputs in image classifications with deep convolutional networks. We leverage so-called boundary samples to enforce low confidence (maximum softmax probabilities) for inputs far away from the training data. In particular, we propose the boundary optimised samples (named BoS) training algorithm for generating them. Unlike existing approaches, it does not require extra generative adversarial network, but achieves the goal by simply back propagating the gradient of an appropriately designed loss function to the input samples. At the end of the BoS training, all the boundary samples are in principle located on a specific level hypersurface with respect to the designed loss. Our contributions are i) the BoS training as an efficient alternative to generate boundary samples, ii) a robust algorithm therewith to enforce low confidence for OOD samples, and iii) experiments demonstrating improved OOD detection over the baseline. We show the performance using standard datasets for training and different test sets including Fashion MNIST, EMNIST, SVHN, and CIFAR-100, preceded by evaluations with a synthetic 2-dimensional dataset that provide an insight for the new procedure.

A Boundary-Aware Distillation Network for Compressed Video Semantic Segmentation

Hongchao Lu

Responsive image

Auto-TLDR; A Boundary-Aware Distillation Network for Video Semantic Segmentation

Slides Poster Similar

In recent years optical flow is often estimated to reuse features so as to accelerate video semantic segmentation. With addition of optical flow network, however, extra cost may incur and accuracy may thus be degraded because of repeated warping operation. In this paper, we propose a boundary-aware distillation network (BDNet) that replaces optical flow network with block motion vectors encoded in compressed video, resulting in negligible computational complexity. In order to make salient features, an auxiliary boundary-aware stream is added to the main stream to jointly estimate silhouette and segmentation of objects. To further correct warped features, a well-trained teacher network is employed to transfer knowledge to the main stream. Both boundary-aware stream and the teacher network are neglected during inference stage, so that video segmentation network enables to get faster without increasing any computational burden. By splitting the task into three components, our BDNet shows almost 10% time saving as well as 1.6% accuracy improvement over baseline on the Cityscapes dataset.

Class-Incremental Learning with Topological Schemas of Memory Spaces

Xinyuan Chang, Xiaoyu Tao, Xiaopeng Hong, Xing Wei, Wei Ke, Yihong Gong

Responsive image

Auto-TLDR; Class-incremental Learning with Topological Schematic Model

Slides Poster Similar

Class-incremental learning (CIL) aims to incrementally learn a unified classifier for new classes emerging, which suffers from the catastrophic forgetting problem. To alleviate forgetting and improve the recognition performance, we propose a novel CIL framework, named the topological schemas model (TSM). TSM consists of a Gaussian mixture model arranged on 2D grids (2D-GMM) as the memory of the learned knowledge. To train the 2D-GMM model, we develop a novel competitive expectation-maximization (CEM) method, which contains a global topology embedding step and a local expectation-maximization finetuning step. Meanwhile, we choose the image samples of old classes that have the maximum posterior probability with respect to each Gaussian distribution as the episodic points. When finetuning for new classes, we propose the memory preservation loss (MPL) term to ensure episodic points still have maximum probabilities with respect to the corresponding Gaussian distribution. MPL preserves the distribution of 2D-GMM for old knowledge during incremental learning and alleviates catastrophic forgetting. Comprehensive experimental evaluations on two popular CIL benchmarks CIFAR100 and subImageNet demonstrate the superiority of our TSM.

FastSal: A Computationally Efficient Network for Visual Saliency Prediction

Feiyan Hu, Kevin Mcguinness

Responsive image

Auto-TLDR; MobileNetV2: A Convolutional Neural Network for Saliency Prediction

Slides Poster Similar

This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget. We modify and test various recent efficient convolutional neural network architectures like EfficientNet and MobileNetV2 and compare them with existing state-of-the-art saliency models such as SalGAN and DeepGaze II both in terms of standard accuracy metrics like AUC and NSS, and in terms of the computational complexity and model size. We find that MobileNetV2 makes an excellent backbone for a visual saliency model and can be effective even without a complex decoder. We also show that knowledge transfer from a more computationally expensive model like DeepGaze II can be achieved via pseudo-labelling an unlabelled dataset, and that this approach gives result on-par with many state-of-the-art algorithms with a fraction of the computational cost and model size.

Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning

Christian Haase-Schütz, Rainer Stal, Heinz Hertlein, Bernhard Sick

Responsive image

Auto-TLDR; Meta Training and Labelling for Unlabelled Data

Slides Poster Similar

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to labelling errors in this data, typically resulting in large efforts and costs and therefore limiting the applicability of deep learning. To alleviate this issue, we propose a novel meta training and labelling scheme that is able to use inexpensive unlabelled data by taking advantage of the generalization power of deep neural networks. We show experimentally that by solely relying on one network architecture and our proposed scheme of combining self-training with pseudolabels, both label quality and resulting model accuracy, can be improved significantly. Our method achieves state-of-the-art results, while being architecture agnostic and therefore broadly applicable. Compared to other methods dealing with erroneous labels, our approach does neither require another network to be trained, nor does it necessarily need an additional, highly accurate reference label set. Instead of removing samples from a labelled set, our technique uses additional sensor data without the need for manual labelling. Furthermore, our approach can be used for semi-supervised learning.

Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?

Xiang Deng, Zhongfei Zhang

Responsive image

Auto-TLDR; Meta-learning Based Training of Deep Neural Networks for Few-Shot Learning

Slides Poster Similar

Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more parameters. On the other hand, meta-learning approaches exhibit powerful generalization on new tasks in few-shot learning. Intuitively, few-shot learning is more challenging than the standard supervised learning as each target class only has a very few or no training samples. The natural question that arises is whether the meta-learning idea can be used for improving the generalization of DNNs on the standard supervised learning. In this paper, we propose a novel meta-learning based training procedure (MLTP) for DNNs and demonstrate that the meta-learning idea can indeed improve the generalization abilities of DNNs. MLTP simulates the meta-training process by considering a batch of training samples as a task. The key idea is that the gradient descent step for improving the current task performance should also improve a new task performance, which is ignored by the current standard procedure for training neural networks. MLTP also benefits from all the existing training techniques such as dropout, weight decay, and batch normalization. We evaluate MLTP by training a variety of small and large neural networks on three benchmark datasets, i.e., CIFAR-10, CIFAR-100, and Tiny ImageNet. The experimental results show a consistently improved generalization performance on all the DNNs with different sizes, which verifies the promise of MLTP and demonstrates that the meta-learning idea is indeed able to improve the generalization of DNNs on the standard supervised learning.

Adversarial Knowledge Distillation for a Compact Generator

Hideki Tsunashima, Shigeo Morishima, Junji Yamato, Qiu Chen, Hirokatsu Kataoka

Responsive image

Auto-TLDR; Adversarial Knowledge Distillation for Generative Adversarial Nets

Slides Poster Similar

In this paper, we propose memory-efficient Generative Adversarial Nets (GANs) in line with knowledge distillation. Most existing GANs have a shortcoming in terms of the number of model parameters and low processing speed. Here, to tackle the problem, we propose Adversarial Knowledge Distillation for Generative models (AKDG) for highly efficient GANs, in terms of unconditional generation. Using AKDG, model size and processing speed are substantively reduced. Through an adversarial training exercise with a distillation discriminator, a student generator successfully mimics a teacher generator in fewer model layers and fewer parameters and at a higher processing speed. Moreover, our AKDG is network architecture-agnostic. Comparison of AKDG-applied models to vanilla models suggests that it achieves closer scores to a teacher generator and more efficient performance than a baseline method with respect to Inception Score (IS) and Frechet Inception Distance (FID). In CIFAR-10 experiments, improving IS/FID 1.17pt/55.19pt and in LSUN bedroom experiments, improving FID 71.1pt in comparison to the conventional distillation method for GANs.

Quasibinary Classifier for Images with Zero and Multiple Labels

Liao Shuai, Efstratios Gavves, Changyong Oh, Cees Snoek

Responsive image

Auto-TLDR; Quasibinary Classifiers for Zero-label and Multi-label Classification

Slides Poster Similar

The softmax and binary classifier are commonly preferred for image classification applications. However, as softmax is specifically designed for categorical classification, it assumes each image has just one class label. This limits its applicability for problems where the number of labels does not equal one, most notably zero- and multi-label problems. In these challenging settings, binary classifiers are, in theory, better suited. However, as they ignore the correlation between classes, they are not as accurate and scalable in practice. In this paper, we start from the observation that the only difference between binary and softmax classifiers is their normalization function. Specifically, while the binary classifier self-normalizes its score, the softmax classifier combines the scores from all classes before normalization. On the basis of this observation we introduce a normalization function that is learnable, constant, and shared between classes and data points. By doing so, we arrive at a new type of binary classifier that we coin quasibinary classifier. We show in a variety of image classification settings, and on several datasets, that quasibinary classifiers are considerably better in classification settings where regular binary and softmax classifiers suffer, including zero-label and multi-label classification. What is more, we show that quasibinary classifiers yield well-calibrated probabilities allowing for direct and reliable comparisons, not only between classes but also between data points.

Smart Inference for Multidigit Convolutional Neural Network Based Barcode Decoding

Duy-Thao Do, Tolcha Yalew, Tae Joon Jun, Daeyoung Kim

Responsive image

Auto-TLDR; Smart Inference for Barcode Decoding using Deep Convolutional Neural Network

Slides Poster Similar

Barcodes are ubiquitous and have been used in most of critical daily activities for decades. However, most of traditional decoders require well-founded barcode under a relatively standard condition. While wilder conditioned barcodes such as underexposed, occluded, blurry, wrinkled and rotated are commonly captured in reality, those traditional decoders show weakness of recognizing. Several works attempted to solve those challenging barcodes, but many limitations still exist. This work aims to solve the decoding problem using deep convolutional neural network with the possibility of running on portable devices. Firstly, we proposed a special modification of inference based on the feature of having checksum and test-time augmentation, named as Smart Inference (SI) in prediction phase of a trained model. SI considerably boosts accuracy and reduces the false prediction for trained models. Secondly, we have created a large practical evaluation dataset of real captured 1D barcode under various challenging conditions to test our methods vigorously, which is publicly available for other researchers. The experiments' results demonstrated the SI effectiveness with the highest accuracy of 95.85% which outperformed many existing decoders on the evaluation set. Finally, we successfully minimized the best model by knowledge distillation to a shallow model which is shown to have high accuracy (90.85%) with good inference speed of 34.2 ms per image on a real edge device.

Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks

Sebastian Palacio, Philipp Engler, Jörn Hees, Andreas Dengel

Responsive image

Auto-TLDR; Self-Supervised Autogenous Learning for Deep Neural Networks

Slides Poster Similar

Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross- entropy loss). This setup dismisses all kinds of supporting signals that can be used to reinforce the existence or absence of particular patterns. The increasing need for models that are interpretable by design makes the inclusion of said contextual signals a crucial necessity. To this end, we introduce the notion of Self-Supervised Autogenous Learning (SSAL). A SSAL objective is realized through one or more additional targets that are derived from the original supervised classification task, following architectural principles found in multi-task learning. SSAL branches impose low-level priors into the optimization process (e.g., grouping). The ability of using SSAL branches during inference, allow models to converge faster, focusing on a richer set of class-relevant features. We equip state-of-the-art DNNs with SSAL objectives and report consistent improvements for all of them on CIFAR100 and Imagenet. We show that SSAL models outperform similar state-of-the-art methods focused on contextual loss functions, auxiliary branches and hierarchical priors.

Adaptive Distillation for Decentralized Learning from Heterogeneous Clients

Jiaxin Ma, Ryo Yonetani, Zahid Iqbal

Responsive image

Auto-TLDR; Decentralized Learning via Adaptive Distillation

Slides Poster Similar

This paper addresses the problem of decentralized learning to achieve a high-performance global model by asking a group of clients to share local models pre-trained with their own data resources. We are particularly interested in a specific case where both the client model architectures and data distributions are diverse, which makes it nontrivial to adopt conventional approaches such as Federated Learning and network co-distillation. To this end, we propose a new decentralized learning method called Decentralized Learning via Adaptive Distillation (DLAD). Given a collection of client models and a large number of unlabeled distillation samples, the proposed DLAD 1) aggregates the outputs of the client models while adaptively emphasizing those with higher confidence in given distillation samples and 2) trains the global model to imitate the aggregated outputs. Our extensive experimental evaluation on multiple public datasets (MNIST, CIFAR-10, and CINIC-10) demonstrates the effectiveness of the proposed method.

Teacher-Student Competition for Unsupervised Domain Adaptation

Ruixin Xiao, Zhilei Liu, Baoyuan Wu

Responsive image

Auto-TLDR; Unsupervised Domain Adaption with Teacher-Student Competition

Slides Poster Similar

With the supervision from source domain only in class-level, existing unsupervised domain adaption (UDA) methods mainly learn the domain-invariant representations from a shared feature extractor, which cause the source-bias problem. This paper proposes an unsupervised domain adaption approach with Teacher-Student Competition (TSC). In particular, a student network is introduced to learn the target-specific feature space, and we design a novel competition mechanism to select more credible pseudo-labels for the training of student network. We introduce a teacher network with the structure of existing conventional UDA method, and both teacher and student networks compete to provide target pseudo-labels to constrain every target sample's training in student network. Extensive experiments demonstrate that our proposed TSC framework significantly outperforms the state-of-the-art domain adaption methods on Office-31 and ImageCLEF-DA benchmarks.

Multi-Order Feature Statistical Model for Fine-Grained Visual Categorization

Qingtao Wang, Ke Zhang, Shaoli Huang, Lianbo Zhang, Jin Fan

Responsive image

Auto-TLDR; Multi-Order Feature Statistical Method for Fine-Grained Visual Categorization

Slides Poster Similar

Fine-grained visual categorization aims to learn a robust image representation modeling subtle differences from similar categories. Existing methods in this field tackle the problem by designing complex frameworks, which produce high-level features by performing first-order or second-order pooling. Despite the impressive performance achieved by these strategies, the single-order networks only carry linear or non-linear information of the last convolutional layer, neglecting the fact that feature from different orders are mutually complementary. In this paper, we propose a Multi-Order Feature Statistical Method (MOFS), which learns fine-grained features characterizing multiple orders. Specifically, the MOFS consists of two sub-modules: (i) a first-order module modeling both mid-level and high-level features. (ii) a covariance feature statistical module capturing high-order features. By deploying these two sub-modules on the top of existing backbone networks, MOFS simultaneously captures multi-level of discrimative patters including local, global and co-related patters. We evaluate the proposed method on three challenging benchmarks, namely CUB-200-2011, Stanford Cars, and FGVC-Aircraft. Compared with state-of-the-art methods, experiments results exhibit superior performance in recognizing fine-grained objects

A Delayed Elastic-Net Approach for Performing Adversarial Attacks

Brais Cancela, Veronica Bolon-Canedo, Amparo Alonso-Betanzos

Responsive image

Auto-TLDR; Robustness of ImageNet Pretrained Models against Adversarial Attacks

Slides Poster Similar

With the rise of the so-called Adversarial Attacks, there is an increased concern on model security. In this paper we present two different contributions: novel measures of robustness (based on adversarial attacks) and a novel adversarial attack. The key idea behind these metrics is to obtain a measure that could compare different architectures, with independence of how the input is preprocessed (robustness against different input sizes and value ranges). To do so, a novel adversarial attack is presented, performing a delayed elastic-net adversarial attack (constraints are only used whenever a successful adversarial attack is obtained). Experimental results show that our approach obtains state-of-the-art adversarial samples, in terms of minimal perturbation distance. Finally, a benchmark of ImageNet pretrained models is used to conduct experiments aiming to shed some light about which model should be selected whenever security is a role factor.

Meta Soft Label Generation for Noisy Labels

Görkem Algan, Ilkay Ulusoy

Responsive image

Auto-TLDR; MSLG: Meta-Learning for Noisy Label Generation

Slides Poster Similar

The existence of noisy labels in the dataset causes significant performance degradation for deep neural networks (DNNs). To address this problem, we propose a Meta Soft Label Generation algorithm called MSLG, which can jointly generate soft labels using meta-learning techniques and learn DNN parameters in an end-to-end fashion. Our approach adapts the meta-learning paradigm to estimate optimal label distribution by checking gradient directions on both noisy training data and noise-free meta-data. In order to iteratively update soft labels, meta-gradient descent step is performed on estimated labels, which would minimize the loss of noise-free meta samples. In each iteration, the base classifier is trained on estimated meta labels. MSLG is model-agnostic and can be added on top of any existing model at hand with ease. We performed extensive experiments on CIFAR10, Clothing1M and Food101N datasets. Results show that our approach outperforms other state-of-the-art methods by a large margin. Our code is available at \url{https://github.com/gorkemalgan/MSLG_noisy_label}.

Teacher-Student Training and Triplet Loss for Facial Expression Recognition under Occlusion

Mariana-Iuliana Georgescu, Radu Ionescu

Responsive image

Auto-TLDR; Knowledge Distillation for Facial Expression Recognition under Occlusion

Slides Similar

In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous studies show that pre-training convolutional neural networks (CNNs) on fully-visible (non-occluded) faces improves the accuracy, we propose to employ knowledge distillation to achieve further improvements. First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a CNN trained on occluded faces. Second of all, we propose a new approach for knowledge distillation based on triplet loss. During training, the goal is to reduce the distance between an anchor embedding, produced by a student CNN that takes occluded faces as input, and a positive embedding (from the same class as the anchor), produced by a teacher CNN trained on fully-visible faces, so that it becomes smaller than the distance between the anchor and a negative embedding (from a different class than the anchor), produced by the student CNN. Third of all, we propose to combine the distilled embeddings obtained through the classic teacher-student strategy and our novel teacher-student strategy based on triplet loss into a single embedding vector. We conduct experiments on two benchmarks, FER+ and AffectNet, with two CNN architectures, VGG-f and VGG-face, showing that knowledge distillation can bring significant improvements over the state-of-the-art methods designed for occluded faces in the VR setting. Furthermore, we obtain accuracy rates that are quite close to the state-of-the-art models that take as input fully-visible faces. For example, on the FER+ data set, our VGG-face based on concatenated distilled embeddings attains an accuracy rate of 82.75% on lower-half-visible faces, which is only 2.24% below the accuracy rate of a state-of-the-art VGG-13 that is evaluated on fully-visible faces. Given that our model sees only the lower-half of the face, we consider this to be a remarkable achievement. In conclusion, we consider that our distilled CNN models can provide useful feedback for the task of recognizing the facial expressions of a person wearing a VR headset.

Image Representation Learning by Transformation Regression

Xifeng Guo, Jiyuan Liu, Sihang Zhou, En Zhu, Shihao Dong

Responsive image

Auto-TLDR; Self-supervised Image Representation Learning using Continuous Parameter Prediction

Slides Poster Similar

Self-supervised learning is a thriving research direction since it can relieve the burden of human labeling for machine learning by seeking for supervision from data instead of human annotation. Although demonstrating promising performance in various applications, we observe that the existing methods usually model the auxiliary learning tasks as classification tasks with finite discrete labels, leading to insufficient supervisory signals, which in turn restricts the representation quality. In this paper, to solve the above problem and make full use of the supervision from data, we design a regression model to predict the continuous parameters of a group of transformations, i.e., image rotation, translation, and scaling. Surprisingly, this naive modification stimulates tremendous potential from data and the resulting supervisory signal has largely improved the performance of image representation learning. Extensive experiments on four image datasets, including CIFAR10, CIFAR100, STL10, and SVHN, indicate that our proposed algorithm outperforms the state-of-the-art unsupervised learning methods by a large margin in terms of classification accuracy. Crucially, we find that with our proposed training mechanism as an initialization, the performance of the existing state-of-the-art classification deep architectures can be preferably improved.

Beyond Cross-Entropy: Learning Highly Separable Feature Distributions for Robust and Accurate Classification

Arslan Ali, Andrea Migliorati, Tiziano Bianchi, Enrico Magli

Responsive image

Auto-TLDR; Gaussian class-conditional simplex loss for adversarial robust multiclass classifiers

Slides Poster Similar

Deep learning has shown outstanding performance in several applications including image classification. However, deep classifiers are known to be highly vulnerable to adversarial attacks, in that a minor perturbation of the input can easily lead to an error. Providing robustness to adversarial attacks is a very challenging task especially in problems involving a large number of classes, as it typically comes at the expense of an accuracy decrease. In this work, we propose the Gaussian class-conditional simplex (GCCS) loss: a novel approach for training deep robust multiclass classifiers that provides adversarial robustness while at the same time achieving or even surpassing the classification accuracy of state-of-the-art methods. Differently from other frameworks, the proposed method learns a mapping of the input classes onto target distributions in a latent space such that the classes are linearly separable. Instead of maximizing the likelihood of target labels for individual samples, our objective function pushes the network to produce feature distributions yielding high inter-class separation. The mean values of the distributions are centered on the vertices of a simplex such that each class is at the same distance from every other class. We show that the regularization of the latent space based on our approach yields excellent classification accuracy and inherently provides robustness to multiple adversarial attacks, both targeted and untargeted, outperforming state-of-the-art approaches over challenging datasets.

Verifying the Causes of Adversarial Examples

Honglin Li, Yifei Fan, Frieder Ganz, Tony Yezzi, Payam Barnaghi

Responsive image

Auto-TLDR; Exploring the Causes of Adversarial Examples in Neural Networks

Slides Poster Similar

The robustness of neural networks is challenged by adversarial examples that contain almost imperceptible perturbations to inputs which mislead a classifier to incorrect outputs in high confidence. Limited by the extreme difficulty in examining a high-dimensional image space thoroughly, research on explaining and justifying the causes of adversarial examples falls behind studies on attacks and defenses. In this paper, we present a collection of potential causes of adversarial examples and verify (or partially verify) them through carefully-designed controlled experiments. The major causes of adversarial examples include model linearity, one-sum constraint, and geometry of the categories. To control the effect of those causes, multiple techniques are applied such as $L_2$ normalization, replacement of loss functions, construction of reference datasets, and novel models using multi-layer perceptron probabilistic neural networks (MLP-PNN) and density estimation (DE). Our experiment results show that geometric factors tend to be more direct causes and statistical factors magnify the phenomenon, especially for assigning high prediction confidence. We hope this paper will inspire more studies to rigorously investigate the root causes of adversarial examples, which in turn provide useful guidance on designing more robust models.

P-DIFF: Learning Classifier with Noisy Labels Based on Probability Difference Distributions

Wei Hu, Qihao Zhao, Yangyu Huang, Fan Zhang

Responsive image

Auto-TLDR; P-DIFF: A Simple and Effective Training Paradigm for Deep Neural Network Classifier with Noisy Labels

Slides Poster Similar

Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over- fit on these noisy labels due to its high capability. In this paper, we present a very simple but effective training paradigm called P-DIFF, which can train DNN classifiers but obviously alleviate the adverse impact of noisy labels. Our proposed probability difference distribution implicitly reflects the probability of a training sample to be clean, then this probability is employed to re-weight the corresponding sample during the training process. P-DIFF can also achieve good performance even without prior- knowledge on the noise rate of training samples. Experiments on benchmark datasets also demonstrate that P-DIFF is superior to the state-of-the-art sample selection methods.

Revisiting ImprovedGAN with Metric Learning for Semi-Supervised Learning

Jaewoo Park, Yoon Gyo Jung, Andrew Teoh

Responsive image

Auto-TLDR; Improving ImprovedGAN with Metric Learning for Semi-supervised Learning

Slides Poster Similar

Semi-supervised Learning (SSL) is a classical problem where a model needs to solve classification as it is trained on a partially labeled train data. After the introduction of generative adversarial network (GAN) and its success, the model has been modified to be applicable to SSL. ImprovedGAN as a representative model for GAN-based SSL, it showed promising performance on the SSL problem. However, the inner mechanism of this model has been only partially revealed. In this work, we revisit ImprovedGAN with a fresh perspective based on metric learning. In particular, we interpret ImprovedGAN by general pair weighting, a recent framework in metric learning. Based on this interpretation, we derive two theoretical properties of ImprovedGAN: (i) its discriminator learns to make confident predictions over real samples, (ii) the adversarial interaction in ImprovedGAN along with semi-supervision results in cluster separation by reducing intra-class variance and increasing the inter-class variance, thereby improving the model generalization. These theoretical implications are experimentally supported. Motivated by the findings, we propose a variant of ImprovedGAN, called Intensified ImprovedGAN (I2GAN), where its cluster separation characteristic is enhanced by two proposed techniques: (a) the unsupervised discriminator loss is scaled up and (b) the generated batch size is enlarged. As a result, I2GAN produces better class-wise cluster separation and, hence, generalization. Extensive experiments on the widely known benchmark data sets verify the effectiveness of our proposed method, showing that its performance is better than or comparable to other GAN based SSL models.

Rethinking Experience Replay: A Bag of Tricks for Continual Learning

Pietro Buzzega, Matteo Boschini, Angelo Porrello, Simone Calderara

Responsive image

Auto-TLDR; Experience Replay for Continual Learning: A Practical Approach

Slides Poster Similar

In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time. Under these assumptions, it is especially challenging to improve on classes appearing later in the stream while remaining accurate on previous ones. This is due to the infamous problem of catastrophic forgetting, which causes a quick performance degradation when the classifier focuses on learning new categories. Recent literature proposed various approaches to tackle this issue, often resorting to very sophisticated techniques. In this work, we show that naive rehearsal can be patched to achieve similar performance. We point out some shortcomings that restrain Experience Replay (ER) and propose five tricks to mitigate them. Experiments show that ER, thus enhanced, displays an accuracy gain of 51.2 and 26.9 percentage points on the CIFAR-10 and CIFAR-100 datasets respectively (memory buffer size 1000). As a result, it surpasses current state-of-the-art rehearsal-based methods.

Norm Loss: An Efficient yet Effective Regularization Method for Deep Neural Networks

Theodoros Georgiou, Sebastian Schmitt, Thomas Baeck, Wei Chen, Michael Lew

Responsive image

Auto-TLDR; Weight Soft-Regularization with Oblique Manifold for Convolutional Neural Network Training

Slides Poster Similar

Convolutional neural network training can suffer from diverse issues like exploding or vanishing gradients, scaling-based weight space symmetry and covariant-shift. In order to address these issues, researchers develop weight regularization methods and activation normalization methods. In this work we propose a weight soft-regularization method based on the Oblique manifold. The proposed method uses a loss function which pushes each weight vector to have a norm close to one, i.e. the weight matrix is smoothly steered toward the so-called Oblique manifold. We evaluate our method on the very popular CIFAR-10, CIFAR-100 and ImageNet 2012 datasets using two state-of-the-art architectures, namely the ResNet and wide-ResNet. Our method introduces negligible computational overhead and the results show that it is competitive to the state-of-the-art and in some cases superior to it. Additionally, the results are less sensitive to hyperparameter settings such as batch size and regularization factor.

IDA-GAN: A Novel Imbalanced Data Augmentation GAN

Hao Yang, Yun Zhou

Responsive image

Auto-TLDR; IDA-GAN: Generative Adversarial Networks for Imbalanced Data Augmentation

Slides Poster Similar

Class imbalance is a widely existed and challenging problem in real-world applications such as disease diagnosis, fraud detection, network intrusion detection and so on. Due to the scarce of data, it could significantly deteriorate the accuracy of classification. To address this challenge, we propose a novel Imbalanced Data Augmentation Generative Adversarial Networks (GAN) named IDA-GAN as an augmentation tool to deal with the imbalanced dataset. This is a great challenge because it is hard to train a GAN model under this situation. We overcome this issue by coupling Variational autoencoder along with GAN training. Specifically, we introduce the Variational autoencoder to learn the majority and minority class distributions in the latent space, and use the generative model to utilize each class distribution for the subsequent GAN training. The generative model learns useful features to generate target minority-class samples. By comparing with the state-of-the-art GAN models, the experimental results demonstrate that our proposed IDA-GAN could generate more diverse minority samples with better qualities, and it consistently benefits the imbalanced classification task in terms of several widely-used evaluation metrics on five benchmark datasets: MNIST, Fashion-MNIST, SVHN, CIFAR-10 and GTRSB.

MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization

Yangbin Chen, Yun Ma, Tom Ko, Jianping Wang, Qing Li

Responsive image

Auto-TLDR; MetaMix: A Meta-Agnostic Meta-Learning Algorithm for Few-Shot Classification

Slides Poster Similar

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt quickly to new tasks. However, within each episode, current MAML-based algorithms have limitations in forming generalizable decision boundaries using only a few training examples. In this paper, we propose an approach called MetaMix. It generates virtual examples within each episode to regularize the backbone models. MetaMix can be applied in any of the MAML-based algorithms and learn the decision boundaries which are more generalizable to new tasks. Experiments on the mini-ImageNet, CUB, and FC100 datasets show that MetaMix improves the performance of MAML-based algorithms and achieves the state-of-the-art result when applied in Meta-Transfer Learning.

Rethinking of Deep Models Parameters with Respect to Data Distribution

Shitala Prasad, Dongyun Lin, Yiqun Li, Sheng Dong, Zaw Min Oo

Responsive image

Auto-TLDR; A progressive stepwise training strategy for deep neural networks

Slides Poster Similar

The performance of deep learning models are driven by various parameters but to tune all of them every time, for every dataset, is a heuristic practice. In this paper, unlike the common practice of decaying the learning rate, we propose a step-wise training strategy where the learning rate and the batch size are tuned based on the dataset size. Here, the given dataset size is progressively increased during the training to boost the network performance without saturating the learning curve, after certain epochs. We conducted extensive experiments on multiple networks and datasets to validate the proposed training strategy. The experimental results proves our hypothesis that the learning rate, the batch size and the data size are interrelated and can improve the network accuracy if an optimal progressive stepwise training strategy is applied. The proposed strategy also the overall training computational cost is reduced.

Pretraining Image Encoders without Reconstruction Via Feature Prediction Loss

Gustav Grund Pihlgren, Fredrik Sandin, Marcus Liwicki

Responsive image

Auto-TLDR; Feature Prediction Loss for Autoencoder-based Pretraining of Image Encoders

Similar

This work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: The commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction loss proposed here; the latter turning out to be the most efficient choice. Standard auto-encoder pretraining for deep learning tasks is done by comparing the input image and the reconstructed image. Recent work shows that predictions based on embeddings generated by image autoencoders can be improved by training with perceptual loss, i.e., by adding a loss network after the decoding step. So far the autoencoders trained with loss networks implemented an explicit comparison of the original and reconstructed images using the loss network. However, given such a loss network we show that there is no need for the time-consuming task of decoding the entire image. Instead, we propose to decode the features of the loss network, hence the name ``feature prediction loss''. To evaluate this method we perform experiments on three standard publicly available datasets (LunarLander-v2, STL-10, and SVHN) and compare six different procedures for training image encoders (pixel-wise, perceptual similarity, and feature prediction losses; combined with two variations of image and feature encoding/decoding). The embedding-based prediction results show that encoders trained with feature prediction loss is as good or better than those trained with the other two losses. Additionally, the encoder is significantly faster to train using feature prediction loss in comparison to the other losses. The method implementation used in this work is available online: https://github.com/guspih/Perceptual-Autoencoders

Exploiting Knowledge Embedded Soft Labels for Image Recognition

Lixian Yuan, Riquan Chen, Hefeng Wu, Tianshui Chen, Wentao Wang, Pei Chen

Responsive image

Auto-TLDR; A Soft Label Vector for Image Recognition

Slides Poster Similar

Objects from correlated classes usually share highly similar appearances while objects from uncorrelated classes are very different. Most of current image recognition works treat each class independently, which ignores these class correlations and inevitably leads to sub-optimal performance in many cases. Fortunately, object classes inherently form a hierarchy with different levels of abstraction and this hierarchy encodes rich correlations among different classes. In this work, we utilize a soft label vector that encodes the prior knowledge of class correlations as extra regularization to train the image classifiers. Specifically, for each class, instead of simply using a one-hot vector, we assign a high value to its correlated classes and assign small values to those uncorrelated ones, thus generating knowledge embedded soft labels. We conduct experiments on both general and fine-grained image recognition benchmarks and demonstrate its superiority compared with existing methods.

NeuralFP: Out-Of-Distribution Detection Using Fingerprints of Neural Networks

Wei-Han Lee, Steve Millman, Nirmit Desai, Mudhakar Srivatsa, Changchang Liu

Responsive image

Auto-TLDR; NeuralFP: Detecting Out-of-Distribution Records Using Neural Network Models

Slides Poster Similar

Edge devices use neural network models learnt on cloud to predict labels of its data records, which may lead to incorrect predictions especially for records that are different from the data involved in the training process, i.e., out-of-distribution (OOD) records. However, recent efforts in OOD detection either require the retraining of the model or assume the existence of a certain amount of OOD records, thus limiting their application in practice. In this work, we propose a novel OOD detection method (named as NeuralFP) without requiring any access to OOD records, which constructs non-linear fingerprints of neural network models memorizing the information of data observed during training. The key idea of NeuralFP is to exploit the difference in how the neural network model responds to data records in its training set versus data records that are anomalous. Specifically, NeuralFP builds autoencoders for each layer of the neural network model and then carefully analyzes the error distribution of the autocoders in reconstructing the training set to identify OOD records. Through extensive experiments on multiple real-world datasets, we show the effectiveness of NeuralFP in detecting OOD records as well as its advantages over previous approaches. Furthermore, we provide useful guidelines for parameter selection in the practical adoption of NeuralFP.

Knowledge Distillation for Action Anticipation Via Label Smoothing

Guglielmo Camporese, Pasquale Coscia, Antonino Furnari, Giovanni Maria Farinella, Lamberto Ballan

Responsive image

Auto-TLDR; A Multi-Modal Framework for Action Anticipation using Long Short-Term Memory Networks

Slides Poster Similar

Human capability to anticipate near future from visual observations and non-verbal cues is essential for developing intelligent systems that need to interact with people. Several research areas, such as human-robot interaction (HRI), assisted living or autonomous driving need to foresee future events to avoid crashes or help people. Egocentric scenarios are classic examples where action anticipation is applied due to their numerous applications. Such challenging task demands to capture and model domain's hidden structure to reduce prediction uncertainty. Since multiple actions may equally occur in the future, we treat action anticipation as a multi-label problem with missing labels extending the concept of label smoothing. This idea resembles the knowledge distillation process since useful information is injected into the model during training. We implement a multi-modal framework based on long short-term memory (LSTM) networks to summarize past observations and make predictions at different time steps. We perform extensive experiments on EPIC-Kitchens and EGTEA Gaze+ datasets including more than 2500 and 100 action classes, respectively. The experiments show that label smoothing systematically improves performance of state-of-the-art models for action anticipation.

Probability Guided Maxout

Claudio Ferrari, Stefano Berretti, Alberto Del Bimbo

Responsive image

Auto-TLDR; Probability Guided Maxout for CNN Training

Slides Poster Similar

In this paper, we propose an original CNN training strategy that brings together ideas from both dropout-like regularization methods and solutions that learn discriminative features. We propose a dropping criterion that, differently from dropout and its variants, is deterministic rather than random. It grounds on the empirical evidence that feature descriptors with larger $L2$-norm and highly-active nodes are strongly correlated to confident class predictions. Thus, our criterion guides towards dropping a percentage of the most active nodes of the descriptors, proportionally to the estimated class probability. We simultaneously train a per-sample scaling factor to balance the expected output across training and inference. This further allows us to keep high the descriptor's L2-norm, which we show enforces confident predictions. The combination of these two strategies resulted in our ``Probability Guided Maxout'' solution that acts as a training regularizer. We prove the above behaviors by reporting extensive image classification results on the CIFAR10, CIFAR100, and Caltech256 datasets.

Exploiting Distilled Learning for Deep Siamese Tracking

Chengxin Liu, Zhiguo Cao, Wei Li, Yang Xiao, Shuaiyuan Du, Angfan Zhu

Responsive image

Auto-TLDR; Distilled Learning Framework for Siamese Tracking

Slides Poster Similar

Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained devices like mobile phones, given factor that such a deployment normally requires cost-effective considerations. In this work, we address this issue by presenting a novel Distilled Learning Framework(DLF) for siamese tracking, which aims at learning tracking model with efficiency and high accuracy. Specifically, we propose two simple yet effective knowledge distillation strategies, denote as point-wise distillation and pair-wise distillation, which are designed for transferring knowledge from a more discriminative teacher tracker into a compact student tracker. In this way, cost-effective and high performance tracking could be achieved. Extensive experiments on several tracking benchmarks demonstrate the effectiveness of our proposed method.

Fine-Tuning DARTS for Image Classification

Muhammad Suhaib Tanveer, Umar Karim Khan, Chong Min Kyung

Responsive image

Auto-TLDR; Fine-Tune Neural Architecture Search using Fixed Operations

Slides Poster Similar

Neural Architecture Search (NAS) has gained attraction due to superior classification performance. Differential Architecture Search (DARTS) is a computationally light method. To limit computational resources DARTS makes numerous approximations. These approximations result in inferior performance. We propose to fine-tune DARTS using fixed operations as these are independent of these approximations. Our method offers a good trade-off between the number of parameters and classification accuracy. Our approach improves the top-1 accuracy on Fashion-MNIST, CompCars and MIO-TCD datasets by 0.56%, 0.50%, and 0.39%, respectively compared to the state-of-the-art approaches. Our approach performs better than DARTS, improving the accuracy by 0.28%, 1.64%, 0.34%, 4.5%, and 3.27% compared to DARTS, on CIFAR-10, CIFAR-100, Fashion-MNIST, CompCars, and MIO-TCD datasets, respectively.

Generalization Comparison of Deep Neural Networks Via Output Sensitivity

Mahsa Forouzesh, Farnood Salehi, Patrick Thiran

Responsive image

Auto-TLDR; Generalization of Deep Neural Networks using Sensitivity

Slides Similar

Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter by linking the loss function to the output's sensitivity to its input. We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing the generalization performance of networks, without requiring labeled data. We find that sensitivity is decreased by applying popular methods which improve the generalization performance of the model, such as (1) using a deep network rather than a wide one, (2) adding convolutional layers to baseline classifiers instead of adding fully-connected layers, (3) using batch normalization, dropout and max-pooling, and (4) applying parameter initialization techniques.

Improving Batch Normalization with Skewness Reduction for Deep Neural Networks

Pak Lun Kevin Ding, Martin Sarah, Baoxin Li

Responsive image

Auto-TLDR; Batch Normalization with Skewness Reduction

Slides Poster Similar

Batch Normalization (BN) is a well-known technique used in training deep neural networks. The main idea behind batch normalization is to normalize the features of the layers ($i.e.$, transforming them to have a mean equal to zero and a variance equal to one). Such a procedure encourages the optimization landscape of the loss function to be smoother, and improve the learning of the networks for both speed and performance. In this paper, we demonstrate that the performance of the network can be improved, if the distributions of the features of the output in the same layer are similar. As normalizing based on mean and variance does not necessarily make the features to have the same distribution, we propose a new normalization scheme: Batch Normalization with Skewness Reduction (BNSR). Comparing with other normalization approaches, BNSR transforms not just only the mean and variance, but also the skewness of the data. By tackling this property of a distribution, we are able to make the output distributions of the layers to be further similar. The nonlinearity of BNSR may further improve the expressiveness of the underlying network. Comparisons with other normalization schemes are tested on the CIFAR-100 and ImageNet datasets. Experimental results show that the proposed approach can outperform other state-of-the-arts that are not equipped with BNSR.

Adversarially Constrained Interpolation for Unsupervised Domain Adaptation

Mohamed Azzam, Aurele Tohokantche Gnanha, Hau-San Wong, Si Wu

Responsive image

Auto-TLDR; Unsupervised Domain Adaptation with Domain Mixup Strategy

Slides Poster Similar

We address the problem of unsupervised domain adaptation (UDA) which aims at adapting models trained on a labeled domain to a completely unlabeled domain. One way to achieve this goal is to learn a domain-invariant representation. However, this approach is subject to two challenges: samples from two domains are insufficient to guarantee domain-invariance at most part of the latent space, and neighboring samples from the target domain may not belong to the same class on the low-dimensional manifold. To mitigate these shortcomings, we propose two strategies. First, we incorporate a domain mixup strategy in domain adversarial learning model by linearly interpolating between the source and target domain samples. This allows the latent space to be continuous and yields an improvement of the domain matching. Second, the domain discriminator is regularized via judging the relative difference between both domains for the input mixup features, which speeds up the domain matching. Experiment results show that our proposed model achieves a superior performance on different tasks under various domain shifts and data complexity.