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

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.

Similar papers

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.

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.

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.

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}.

Complementing Representation Deficiency in Few-Shot Image Classification: A Meta-Learning Approach

Xian Zhong, Cheng Gu, Wenxin Huang, Lin Li, Shuqin Chen, Chia-Wen Lin

Responsive image

Auto-TLDR; Meta-learning with Complementary Representations Network for Few-Shot Learning

Slides Poster Similar

Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which focuses on quickly adapting a predictor as a base-learner to new tasks, given limited labeled samples. However, a critical challenge for meta-learning is the representation deficiency since it is hard to discover common information from a small number of training samples or even one, as is the representation of key features from such little information. As a result, a meta-learner cannot be trained well in a high-dimensional parameter space to generalize to new tasks. Existing methods mostly resort to extracting less expressive features so as to avoid the representation deficiency. Aiming at learning better representations, we propose a meta-learning approach with complemented representations network (MCRNet) for few-shot image classification. In particular, we embed a latent space, where latent codes are reconstructed with extra representation information to complement the representation deficiency. Furthermore, the latent space is established with variational inference, collaborating well with different base-learners, and can be extended to other models. Finally, our end-to-end framework achieves the state-of-the-art performance in image classification on three standard few-shot learning datasets.

Meta Learning Via Learned Loss

Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Thomas Grefenstette, Ludovic Righetti, Gaurav Sukhatme, Franziska Meier

Responsive image

Auto-TLDR; meta-learning for learning parametric loss functions that generalize across different tasks and model architectures

Slides Similar

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely, we present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures. We develop a pipeline for “meta-training” such loss functions, targeted at maximizing the performance of the model trained under them. The loss landscape produced by our learned losses significantly improves upon the original task-specific losses in both supervised and reinforcement learning tasks. Furthermore, we show that our meta-learning framework is flexible enough to incorporate additional information at meta-train time. This information shapes the learned loss function such that the environment does not need to provide this information during meta-test time.

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.

MaxDropout: Deep Neural Network Regularization Based on Maximum Output Values

Claudio Filipi Gonçalves Santos, Danilo Colombo, Mateus Roder, Joao Paulo Papa

Responsive image

Auto-TLDR; MaxDropout: A Regularizer for Deep Neural Networks

Slides Poster Similar

Different techniques have emerged in the deep learning scenario, such as Convolutional Neural Networks, Deep Belief Networks, and Long Short-Term Memory Networks, to cite a few. In lockstep, regularization methods, which aim to prevent overfitting by penalizing the weight connections, or turning off some units, have been widely studied either. In this paper, we present a novel approach called MaxDropout, a regularizer for deep neural network models that works in a supervised fashion by removing (shutting off) the prominent neurons (i.e., most active) in each hidden layer. The model forces fewer activated units to learn more representative information, thus providing sparsity. Regarding the experiments, we show that it is possible to improve existing neural networks and provide better results in neural networks when Dropout is replaced by MaxDropout. The proposed method was evaluated in image classification, achieving comparable results to existing regularizers, such as Cutout and RandomErasing, also improving the accuracy of neural networks that uses Dropout by replacing the existing layer by MaxDropout.

A Close Look at Deep Learning with Small Data

Lorenzo Brigato, Luca Iocchi

Responsive image

Auto-TLDR; Low-Complex Neural Networks for Small Data Conditions

Slides Poster Similar

In this work, we perform a wide variety of experiments with different Deep Learning architectures in small data conditions. We show that model complexity is a critical factor when only a few samples per class are available. Differently from the literature, we improve the state of the art using low complexity models. We show that standard convolutional neural networks with relatively few parameters are effective in this scenario. In many of our experiments, low complexity models outperform state-of-the-art architectures. Moreover, we propose a novel network that uses an unsupervised loss to regularize its training. Such architecture either improves the results either performs comparably well to low capacity networks. Surprisingly, experiments show that the dynamic data augmentation pipeline is not beneficial in this particular domain. Statically augmenting the dataset might be a promising research direction while dropout maintains its role as a good regularizer.

WeightAlign: Normalizing Activations by Weight Alignment

Xiangwei Shi, Yunqiang Li, Xin Liu, Jan Van Gemert

Responsive image

Auto-TLDR; WeightAlign: Normalization of Activations without Sample Statistics

Slides Poster Similar

Batch normalization (BN) allows training very deep networks by normalizing activations by mini-batch sample statistics which renders BN unstable for small batch sizes. Current small-batch solutions such as Instance Norm, Layer Norm, and Group Norm use channel statistics which can be computed even for a single sample. Such methods are less stable than BN as they critically depend on the statistics of a single input sample. To address this problem, we propose a normalization of activation without sample statistics. We present WeightAlign: a method that normalizes the weights by the mean and scaled standard derivation computed within a filter, which normalizes activations without computing any sample statistics. Our proposed method is independent of batch size and stable over a wide range of batch sizes. Because weight statistics are orthogonal to sample statistics, we can directly combine WeightAlign with any method for activation normalization. We experimentally demonstrate these benefits for classification on CIFAR-10, CIFAR-100, ImageNet, for semantic segmentation on PASCAL VOC 2012 and for domain adaptation on Office-31.

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.

Meta Generalized Network for Few-Shot Classification

Wei Wu, Shanmin Pang, Zhiqiang Tian, Yaochen Li

Responsive image

Auto-TLDR; Meta Generalized Network for Few-Shot Classification

Similar

Few-shot classification aims to learn a well performance model with very limited labeled examples. There are mainly two directions for this aim, namely, meta- and metric-learning. Meta learning trains models in a particular way to fast adapt to new tasks, but it neglects variational features of images. Metric learning considers relationships among same or different classes, however on the downside, it usually fails to achieve competitive performance on unseen boundary examples. In this paper, we propose a Meta Generalized Network (MGNet) that aims to combine advantages of both meta- and metric-learning. There are two novel components in MGNet. Specifically, we first develop a meta backbone training method that both learns a flexible feature extractor and a classifier initializer efficiently, delightedly leading to fast adaption to unseen few-shot tasks without overfitting. Second, we design a trainable adaptive interval model to improve the cosine classifier, which increases the recognition accuracy of hard examples. We train the meta backbone in the training stage by all classes, and fine-tune the meta-backbone as well as train the adaptive classifier in the testing stage.

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.

ARCADe: A Rapid Continual Anomaly Detector

Ahmed Frikha, Denis Krompass, Volker Tresp

Responsive image

Auto-TLDR; ARCADe: A Meta-Learning Approach for Continuous Anomaly Detection

Slides Poster Similar

Although continual learning and anomaly detection have separately been well-studied in previous works, their intersection remains rather unexplored. The present work addresses a learning scenario where a model has to incrementally learn a sequence of anomaly detection tasks, i.e. tasks from which only examples from the normal (majority) class are available for training. We define this novel learning problem of continual anomaly detection (CAD) and formulate it as a meta-learning problem. Moreover, we propose \emph{A Rapid Continual Anomaly Detector (ARCADe)}, an approach to train neural networks to be robust against the major challenges of this new learning problem, namely catastrophic forgetting and overfitting to the majority class. The results of our experiments on three datasets show that, in the CAD problem setting, ARCADe substantially outperforms baselines from the continual learning and anomaly detection literature. Finally, we provide deeper insights into the learning strategy yielded by the proposed meta-learning algorithm.

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.

Task-based Focal Loss for Adversarially Robust Meta-Learning

Yufan Hou, Lixin Zou, Weidong Liu

Responsive image

Auto-TLDR; Task-based Adversarial Focal Loss for Few-shot Meta-Learner

Slides Poster Similar

Adversarial robustness of machine learning has been widely studied in recent years, and a series of effective methods are proposed to resist adversarial attacks. However, less attention is paid to few-shot meta-learners which are much more vulnerable due to the lack of training samples. In this paper, we propose Task-based Adversarial Focal Loss (TAFL) to handle this tough challenge on a typical meta-learner called MAML. More concretely, we regard few-shot classification tasks as normal samples in learning models and apply focal loss mechanism on them. Our proposed method focuses more on adversarially fragile tasks, leading to improvement on overall model robustness. Results of extensive experiments on several benchmarks demonstrate that TAFL can effectively promote the performance of the meta-learner on adversarial examples with elaborately designed perturbations.

Learning to Prune in Training via Dynamic Channel Propagation

Shibo Shen, Rongpeng Li, Zhifeng Zhao, Honggang Zhang, Yugeng Zhou

Responsive image

Auto-TLDR; Dynamic Channel Propagation for Neural Network Pruning

Slides Poster Similar

In this paper, we propose a novel network training mechanism called "dynamic channel propagation" to prune the model during the training period. In particular, we pick up a specific group of channels in each convolutional layer to participate in the forward propagation in training time according to the significance level of channel, which is defined as channel utility. The utility values with respect to all selected channels are updated simultaneously with the error back-propagation process and will constantly change. Furthermore, when the training ends, channels with high utility values are retained whereas those with low utility values are discarded. Hence, our proposed method trains and prunes neural networks simultaneously. We empirically evaluate our novel training method on various representative benchmark datasets and advanced convolutional neural network (CNN) architectures, including VGGNet and ResNet. The experiment results verify superior performance and robust effectiveness of our approach.

Pose-Robust Face Recognition by Deep Meta Capsule Network-Based Equivariant Embedding

Fangyu Wu, Jeremy Simon Smith, Wenjin Lu, Bailing Zhang

Responsive image

Auto-TLDR; Deep Meta Capsule Network-based Equivariant Embedding Model for Pose-Robust Face Recognition

Similar

Despite the exceptional success in face recognition related technologies, handling large pose variations still remains a key challenge. Current techniques for pose-robust face recognition either, directly extract pose-invariant features, or first synthesize a face that matches the target pose before feature extraction. It is more desirable to learn face representations equivariant to pose variations. To this end, this paper proposes a deep meta Capsule network-based Equivariant Embedding Model (DM-CEEM) with three distinct novelties. First, the proposed RB-CapsNet allows DM-CEEM to learn an equivariant embedding for pose variations and achieve the desired transformation for input face images. Second, we introduce a new version of a Capsule network called RB-CapsNet to extend CapsNet to perform a profile-to-frontal face transformation in deep feature space. Third, we train the DM-CEEM in a meta way by treating a single overall classification target as multiple sub-tasks that satisfy certain unknown probabilities. In each sub-task, we sample the support and query sets randomly. The experimental results on both controlled and in-the-wild databases demonstrate the superiority of DM-CEEM over state-of-the-art.

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.

Revisiting the Training of Very Deep Neural Networks without Skip Connections

Oyebade Kayode Oyedotun, Abd El Rahman Shabayek, Djamila Aouada, Bjorn Ottersten

Responsive image

Auto-TLDR; Optimization of Very Deep PlainNets without shortcut connections with 'vanishing and exploding units' activations'

Slides Poster Similar

Deep neural networks (DNNs) with many layers of feature representations yield state-of-the-art results on several difficult learning tasks. However, optimizing very deep DNNs without shortcut connections known as PlainNets, is a notoriously hard problem. Considering the growing interest in this area, this paper investigates holistically two scenarios that plague the training of very deep PlainNets: (1) the relatively popular challenge of 'vanishing and exploding units' activations', and (2) the less investigated 'singularity' problem, which is studied in details in this paper. In contrast to earlier works that study only the saturation and explosion of units' activations in isolation, this paper harmonizes the inconspicuous coexistence of the aforementioned problems for very deep PlainNets. Particularly, we argue that the aforementioned problems would have to be tackled simultaneously for the successful training of very deep PlainNets. Finally, different techniques that can be employed for tackling the optimization problem are discussed, and a specific combination of simple techniques that allows the successful training of PlainNets having up to 100 layers is demonstrated.

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.

On the Information of Feature Maps and Pruning of Deep Neural Networks

Mohammadreza Soltani, Suya Wu, Jie Ding, Robert Ravier, Vahid Tarokh

Responsive image

Auto-TLDR; Compressing Deep Neural Models Using Mutual Information

Slides Poster Similar

A technique for compressing deep neural models achieving competitive performance to state-of-the-art methods is proposed. The approach utilizes the mutual information between the feature maps and the output of the model in order to prune the redundant layers of the network. Extensive numerical experiments on both CIFAR-10, CIFAR-100, and Tiny ImageNet data sets demonstrate that the proposed method can be effective in compressing deep models, both in terms of the numbers of parameters and operations. For instance, by applying the proposed approach to DenseNet model with 0.77 million parameters and 293 million operations for classification of CIFAR-10 data set, a reduction of 62.66% and 41.00% in the number of parameters and the number of operations are respectively achieved, while increasing the test error only by less than 1%.

TAAN: Task-Aware Attention Network for Few-Shot Classification

Zhe Wang, Li Liu, Fanzhang Li

Responsive image

Auto-TLDR; TAAN: Task-Aware Attention Network for Few-Shot Classification

Slides Poster Similar

Few-shot classification aims to recognize unlabeled samples from unseen classes given only a few labeled samples.Current approaches of few-shot learning usually employ a metriclearning framework to learn a feature similarity comparison between a query (test) example and the few support (training) examples. However, these approaches all extract features from samples independently without looking at the entire task as a whole, and so fail to provide an enough discrimination to features. Moreover, the existing approaches lack the ability to select the most relevant features for the task at hand. In this work, we propose a novel algorithm called Task-Aware Attention Network (TAAN) to address the above problems in few-shot classification. By inserting a Task-Relevant Channel Attention Module into metric-based few-shot learners, TAAN generates channel attentions for each sample by aggregating the context of the entire support set and identifies the most relevant features for similarity comparison. The experiment demonstrates that TAAN is competitive in overall performance comparing to the recent state-of-the-art systems and improves the performance considerably over baseline systems on both mini-ImageNet and tiered-ImageNet benchmarks.

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.

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.

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.

Softer Pruning, Incremental Regularization

Linhang Cai, Zhulin An, Yongjun Xu

Responsive image

Auto-TLDR; Asymptotic SofteR Filter Pruning for Deep Neural Network Pruning

Slides Poster Similar

Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the pruned filters is completely dropped. To utilize the trained pruned filters, we proposed a SofteR Filter Pruning (SRFP) method and its variant, Asymptotic SofteR Filter Pruning (ASRFP), simply decaying the pruned weights with a monotonic decreasing parameter. Our methods perform well across various netowrks, datasets and pruning rates, also transferable to weight pruning. On ILSVRC-2012, ASRFP prunes 40% of the parameters on ResNet-34 with 1.63% top-1 and 0.68% top-5 accuracy improvement. In theory, SRFP and ASRFP are an incremental regularization of the pruned filters. Besides, We note that SRFP and ASRFP pursue better results while slowing down the speed of convergence.

E-DNAS: Differentiable Neural Architecture Search for Embedded Systems

Javier García López, Antonio Agudo, Francesc Moreno-Noguer

Responsive image

Auto-TLDR; E-DNAS: Differentiable Architecture Search for Light-Weight Networks for Image Classification

Slides Poster Similar

Designing optimal and light weight networks to fit in resource-limited platforms like mobiles, DSPs or GPUs is a challenging problem with a wide range of interesting applications, {\em e.g.} in embedded systems for autonomous driving. While most approaches are based on manual hyperparameter tuning, there exist a new line of research, the so-called NAS (Neural Architecture Search) methods, that aim to optimize several metrics during the design process, including memory requirements of the network, number of FLOPs, number of MACs (Multiply-ACcumulate operations) or inference latency. However, while NAS methods have shown very promising results, they are still significantly time and cost consuming. In this work we introduce E-DNAS, a differentiable architecture search method, which improves the efficiency of NAS methods in designing light-weight networks for the task of image classification. Concretely, E-DNAS computes, in a differentiable manner, the optimal size of a number of meta-kernels that capture patterns of the input data at different resolutions. We also leverage on the additive property of convolution operations to merge several kernels with different compatible sizes into a single one, reducing thus the number of operations and the time required to estimate the optimal configuration. We evaluate our approach on several datasets to perform classification. We report results in terms of the SoC (System on Chips) metric, typically used in the Texas Instruments TDA2x families for autonomous driving applications. The results show that our approach allows designing low latency architectures significantly faster than state-of-the-art.

Dynamic Multi-Path Neural Network

Yingcheng Su, Yichao Wu, Ken Chen, Ding Liang, Xiaolin Hu

Responsive image

Auto-TLDR; Dynamic Multi-path Neural Network

Slides Similar

Although deeper and larger neural networks have achieved better performance, due to overwhelming burden on computation, they cannot meet the demands of deployment on resource-limited devices. An effective strategy to address this problem is to make use of dynamic inference mechanism, which changes the inference path for different samples at runtime. Existing methods only reduce the depth by skipping an entire specific layer, which may lose important information in this layer. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more topology choices in terms of both width and depth on the fly. For better modelling the inference path selection, we further introduce previous state and object category information to guide the training process. Compared to previous dynamic inference techniques, the proposed method is more flexible and easier to incorporate into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and classification accuracy.

Graph-Based Interpolation of Feature Vectors for Accurate Few-Shot Classification

Yuqing Hu, Vincent Gripon, Stéphane Pateux

Responsive image

Auto-TLDR; Transductive Learning for Few-Shot Classification using Graph Neural Networks

Slides Poster Similar

In few-shot classification, the aim is to learn models able to discriminate classes using only a small number of labeled examples. In this context, works have proposed to introduce Graph Neural Networks (GNNs) aiming at exploiting the information contained in other samples treated concurrently, what is commonly referred to as the transductive setting in the literature. These GNNs are trained all together with a backbone feature extractor. In this paper, we propose a new method that relies on graphs only to interpolate feature vectors instead, resulting in a transductive learning setting with no additional parameters to train. Our proposed method thus exploits two levels of information: a) transfer features obtained on generic datasets, b) transductive information obtained from other samples to be classified. Using standard few-shot vision classification datasets, we demonstrate its ability to bring significant gains compared to other works.

Filter Pruning Using Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks

Kakeru Mitsuno, Takio Kurita

Responsive image

Auto-TLDR; Hierarchical Group Sparse Regularization for Sparse Convolutional Neural Networks

Slides Poster Similar

Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy. In this paper, we propose a filter pruning method using the hierarchical group sparse regularization. It is shown in our previous work that the hierarchical group sparse regularization is effective in obtaining sparse networks in which filters connected to unnecessary channels are automatically close to zero. After training the convolutional neural network with the hierarchical group sparse regularization, the unnecessary filters are selected based on the increase of the classification loss of the randomly selected training samples to obtain a compact network. It is shown that the proposed method can reduce more than 50% parameters of ResNet for CIFAR-10 with only 0.3% decrease in the accuracy of test samples. Also, 34% parameters of ResNet are reduced for TinyImageNet-200 with higher accuracy than the baseline network.

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.

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.

Hcore-Init: Neural Network Initialization Based on Graph Degeneracy

Stratis Limnios, George Dasoulas, Dimitrios Thilikos, Michalis Vazirgiannis

Responsive image

Auto-TLDR; K-hypercore: Graph Mining for Deep Neural Networks

Slides Poster Similar

Neural networks are the pinnacle of Artificial Intelligence, as in recent years we witnessed many novel architectures, learning and optimization techniques for deep learning. Capitalizing on the fact that neural networks inherently constitute multipartite graphs among neuron layers, we aim to analyze directly their structure to extract meaningful information that can improve the learning process. To our knowledge graph mining techniques for enhancing learning in neural networks have not been thoroughly investigated. In this paper we propose an adapted version of the k-core structure for the complete weighted multipartite graph extracted from a deep learning architecture. As a multipartite graph is a combination of bipartite graphs, that are in turn the incidence graphs of hypergraphs, we design k-hypercore decomposition, the hypergraph analogue of k-core degeneracy. We applied k-hypercore to several neural network architectures, more specifically to convolutional neural networks and multilayer perceptrons for image recognition tasks after a very short pretraining. Then we used the information provided by the hypercore numbers of the neurons to re-initialize the weights of the neural network, thus biasing the gradient optimization scheme. Extensive experiments proved that k-hypercore outperforms the state-of-the-art initialization methods.

Slimming ResNet by Slimming Shortcut

Donggyu Joo, Doyeon Kim, Junmo Kim

Responsive image

Auto-TLDR; SSPruning: Slimming Shortcut Pruning on ResNet Based Networks

Slides Poster Similar

Conventional network pruning methods on convolutional neural networks (CNNs) reduce the number of input or output channels of convolution layers. With these approaches, the channels in the plain network can be pruned without any restrictions. However, in case of the ResNet based networks which have shortcuts (skip connections), the channel slimming of existing pruning methods is limited to the inside of each residual block. Since the number of Flops and parameters are also highly related to the number of channels in the shortcuts, more investigation on pruning channels in shortcuts is required. In this paper, we propose a novel pruning method, Slimming Shortcut Pruning (SSPruning), for pruning channels in shortcuts on ResNet based networks. First, we separate the long shortcut in individual regions that can be pruned independently without considering its long connections. Then, by applying our Importance Learning Gate (ILG) which learns the importance of channels globally regardless of channel type and location (i.e., in the shortcut or inside of the block), we can finally achieve an optimally pruned model. Through various experiments, we have confirmed that our method yields outstanding results when we prune the shortcuts and inside of the block together.

Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study

Veysel Kocaman, Ofer M. Shir, Thomas Baeck

Responsive image

Auto-TLDR; Exploiting Batch Normalization before the Output Layer in Deep Learning for Minority Class Detection in Imbalanced Data Sets

Slides Poster Similar

Some real-world domains, such as Agriculture and Healthcare, comprise early-stage disease indications whose recording constitutes a rare event, and yet, whose precise detection at that stage is critical. In this type of highly imbalanced classification problems, which encompass complex features, deep learning (DL) is much needed because of its strong detection capabilities. At the same time, DL is observed in practice to favor majority over minority classes and consequently suffer from inaccurate detection of the targeted early-stage indications. To simulate such scenarios, we artificially generate skewness (99% vs. 1%) for certain plant types out of the PlantVillage dataset as a basis for classification of scarce visual cues through transfer learning. By randomly and unevenly picking healthy and unhealthy samples from certain plant types to form a training set, we consider a base experiment as fine-tuning ResNet34 and VGG19 architectures and then testing the model performance on a balanced dataset of healthy and unhealthy images. We empirically observe that the initial F1 test score jumps from 0.29 to 0.95 for the minority class upon adding a final Batch Normalization (BN) layer just before the output layer in VGG19. We demonstrate that utilizing an additional BN layer before the output layer in modern CNN architectures has a considerable impact in terms of minimizing the training time and testing error for minority classes in highly imbalanced data sets. Moreover, when the final BN is employed, trying to minimize validation and training losses may not be an optimal way for getting a high F1 test score for minority classes in anomaly detection problems. That is, the network might perform better even if it is not ‘confident’ enough while making a prediction; leading to another discussion about why softmax output is not a good uncertainty measure for DL models.

HFP: Hardware-Aware Filter Pruning for Deep Convolutional Neural Networks Acceleration

Fang Yu, Chuanqi Han, Pengcheng Wang, Ruoran Huang, Xi Huang, Li Cui

Responsive image

Auto-TLDR; Hardware-Aware Filter Pruning for Convolutional Neural Networks

Slides Poster Similar

Convolutional Neural Networks (CNNs) are powerful but computationally demanding and memory intensive, thus impeding their practical applications on resource-constrained hardware. Filter pruning is an efficient approach for deep CNN compression and acceleration, which aims to eliminate some filters with tolerable performance degradation. In the literature, the majority of approaches prune networks by defining the redundant filters or training the networks with a sparsity prior loss function. These approaches mainly use FLOPs as their speed metric. However, the inference latency of pruned networks cannot be directly controlled on the hardware platform, which is an important dimension of practicality. To address this issue, we propose a novel Hardware-aware Filter Pruning method (HFP) which can produce pruned networks that satisfy the actual latency budget on the hardwares of interest. In addition, we propose an iterative pruning framework called Opti-Cut to decrease the accuracy degradation of pruning process and accelerate the pruning procedure whilst meeting the hardware budget. More specifically, HFP first builds up a lookup table for fast estimating the latency of target network about filter configuration layer by layer. Then, HFP leverages information gain (IG) to globally evaluate the filters' contribution to network output distribution. HFP utilizes the Opti-Cut framework to globally prune filters with the minimum IG one by one until the latency budget is satisfied. We verify the effectiveness of the proposed method on CIFAR-10 and ImageNet. Compared with the state-of-the-art pruning methods, HFP demonstrates superior performances on VGGNet, ResNet and MobileNet V1/V2.

How Does DCNN Make Decisions?

Yi Lin, Namin Wang, Xiaoqing Ma, Ziwei Li, Gang Bai

Responsive image

Auto-TLDR; Exploring Deep Convolutional Neural Network's Decision-Making Interpretability

Slides Poster Similar

Deep Convolutional Neural Networks (DCNN), despite imitating the human visual system, present no such decision credibility as human observers. This phenomenon, therefore, leads to the limitations of DCNN's applications in the security and trusted computing, such as self-driving cars and medical diagnosis. Focusing on this issue, our work aims to explore the way DCNN makes decisions. In this paper, the major contributions we made are: firstly, provide the hypothesis, “point-wise activation” of convolution function, according to the analysis of DCNN’s architectures and training process; secondly, point out the effect of “point-wise activation” on DCNN’s uninterpretable classification and pool robustness, and then suggest, in particular, the contradiction between the traditional and DCNN’s convolution kernel functions; finally, distinguish decision-making interpretability from semantic interpretability, and indicate that DCNN’s decision-making mechanism need to evolve towards the direction of semantics in the future. Besides, the “point-wise activation” hypothesis and conclusions proposed in our paper are supported by extensive experimental results.

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 Similar

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.

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.

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.

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.

Filtered Batch Normalization

András Horváth, Jalal Al-Afandi

Responsive image

Auto-TLDR; Batch Normalization with Out-of-Distribution Activations in Deep Neural Networks

Slides Poster Similar

It is a common assumption that the activation of different layers in neural networks follow Gaussian distribution. This distribution can be transformed using normalization techniques, such as batch-normalization, increasing convergence speed and improving accuracy. In this paper we would like to demonstrate, that activations do not necessarily follow Gaussian distribution in all layers. Neurons in deeper layers are more and more specific which can result extremely large, out-of-distribution activations. We will demonstrate that one can create more consistent mean and variance values for batch normalization during training by filtering out these activations which can further improve convergence speed and yield higher validation accuracy.

Learning Sparse Deep Neural Networks Using Efficient Structured Projections on Convex Constraints for Green AI

Michel Barlaud, Frederic Guyard

Responsive image

Auto-TLDR; Constrained Deep Neural Network with Constrained Splitting Projection

Slides Poster Similar

In recent years, deep neural networks (DNN) have been applied to different domains and achieved dramatic performance improvements over state-of-the-art classical methods. These performances of DNNs were however often obtained with networks containing millions of parameters and which training required heavy computational power. In order to cope with this computational issue a huge literature deals with proximal regularization methods which are time consuming.\\ In this paper, we propose instead a constrained approach. We provide the general framework for our new splitting projection gradient method. Our splitting algorithm iterates a gradient step and a projection on convex sets. We study algorithms for different constraints: the classical $\ell_1$ unstructured constraint and structured constraints such as the nuclear norm, the $\ell_{2,1} $ constraint (Group LASSO). We propose a new $\ell_{1,1} $ structured constraint for which we provide a new projection algorithm We demonstrate the effectiveness of our method on three popular datasets (MNIST, Fashion MNIST and CIFAR). Experiments on these datasets show that our splitting projection method with our new $\ell_{1,1} $ structured constraint provides the best reduction of memory and computational power. Experiments show that fully connected linear DNN are more efficient for green AI.

Augmented Bi-Path Network for Few-Shot Learning

Baoming Yan, Chen Zhou, Bo Zhao, Kan Guo, Yang Jiang, Xiaobo Li, Zhang Ming, Yizhou Wang

Responsive image

Auto-TLDR; Augmented Bi-path Network for Few-shot Learning

Slides Poster Similar

Few-shot Learning (FSL) which aims to learn from few labeled training data is becoming a popular research topic, due to the expensive labeling cost in many real-world applications. One kind of successful FSL method learns to compare the testing (query) image and training (support) image by simply concatenating the features of two images and feeding it into the neural network. However, with few labeled data in each class, the neural network has difficulty in learning or comparing the local features of two images. Such simple image-level comparison may cause serious mis-classification. To solve this problem, we propose Augmented Bi-path Network (ABNet) for learning to compare both global and local features on multi-scales. Specifically, the salient patches are extracted and embedded as the local features for every image. Then, the model learns to augment the features for better robustness. Finally, the model learns to compare global and local features separately, \emph{i.e.}, in two paths, before merging the similarities. Extensive experiments show that the proposed ABNet outperforms the state-of-the-art methods. Both quantitative and visual ablation studies are provided to verify that the proposed modules lead to more precise comparison results.

Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks

Jie Ran, Rui Lin, Hayden Kwok-Hay So, Graziano Chesi, Ngai Wong

Responsive image

Auto-TLDR; Nuclear-Norm Rank Minimization Factorization for Deep Neural Networks

Slides Poster Similar

Elasticities in depth, width, kernel size and resolution have been explored in compressing deep neural networks (DNNs). Recognizing that the kernels in a convolutional neural network (CNN) are 4-way tensors, we further exploit a new elasticity dimension along the input-output channels. Specifically, a novel nuclear-norm rank minimization factorization (NRMF) approach is proposed to dynamically and globally search for the reduced tensor ranks during training. Correlation between tensor ranks across multiple layers is revealed, and a graceful tradeoff between model size and accuracy is obtained. Experiments then show the superiority of NRMF over the previous non-elastic variational Bayesian matrix factorization (VBMF) scheme.

CQNN: Convolutional Quadratic Neural Networks

Pranav Mantini, Shishir Shah

Responsive image

Auto-TLDR; Quadratic Neural Network for Image Classification

Slides Poster Similar

Image classification is a fundamental task in computer vision. A variety of deep learning models based on the Convolutional Neural Network (CNN) architecture have proven to be an efficient solution. Numerous improvements have been proposed over the years, where broader, deeper, and denser networks have been constructed. However, the atomic operation for these models has remained a linear unit (single neuron). In this work, we pursue an alternative dimension by hypothesizing the atomic operation to be performed by a quadratic unit. We construct convolutional layers using quadratic neurons for feature extraction and subsequently use dense layers for classification. We perform analysis to quantify the implication of replacing linear neurons with quadratic units. Results show a keen improvement in classification accuracy with quadratic neurons over linear neurons.

Neuron-Based Network Pruning Based on Majority Voting

Ali Alqahtani, Xianghua Xie, Ehab Essa, Mark W. Jones

Responsive image

Auto-TLDR; Large-Scale Neural Network Pruning using Majority Voting

Slides Poster Similar

The achievement of neural networks in a variety of applications is accompanied by a dramatic increase in computational costs and memory requirements. In this paper, we propose an efficient method to simultaneously identify the critical neurons and prune the model during training without involving any pre-training or fine-tuning procedures. Unlike existing methods, which accomplish this task in a greedy fashion, we propose a majority voting technique to compare the activation values among neurons and assign a voting score to quantitatively evaluate their importance.This mechanism helps to effectively reduce model complexity by eliminating the less influential neurons and aims to determine a subset of the whole model that can represent the reference model with much fewer parameters within the training process. Experimental results show that majority voting efficiently compresses the network with no drop in model accuracy, pruning more than 79\% of the original model parameters on CIFAR10 and more than 91\% of the original parameters on MNIST. Moreover, we show that with our proposed method, sparse models can be further pruned into even smaller models by removing more than 60\% of the parameters, whilst preserving the reference model accuracy.