A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata

Tobia Tesan, Pasquale Coscia, Lamberto Ballan

Responsive image

Auto-TLDR; Context-Based Image Annotation with Multiple Semantic Embeddings and Recurrent Neural Networks

Slides Poster

Images represent a commonly used form of visual communication among people. Nevertheless, image classification may be a challenging task when dealing with unclear or non-common images needing more context to be correctly annotated. Metadata accompanying images on social-media represent an ideal source of additional information for retrieving proper neighborhoods easing image annotation task. To this end, we blend visual features extracted from neighbors and their metadata to jointly leverage context and visual cues. Our models use multiple semantic embeddings to achieve the dual objective of being robust to vocabulary changes between train and test sets and decoupling the architecture from the low-level metadata representation. Convolutional and recurrent neural networks (CNNs-RNNs) are jointly adopted to infer similarity among neighbors and query images. We perform comprehensive experiments on the NUS-WIDE dataset showing that our models outperform state-of-the-art architectures based on images and metadata, and decrease both sensory and semantic gaps to better annotate images.

Similar papers

Webly Supervised Image-Text Embedding with Noisy Tag Refinement

Niluthpol Mithun, Ravdeep Pasricha, Evangelos Papalexakis, Amit Roy-Chowdhury

Responsive image

Auto-TLDR; Robust Joint Embedding for Image-Text Retrieval Using Web Images

Slides Similar

In this paper, we address the problem of utilizing web images in training robust joint embedding models for the image-text retrieval task. Prior webly supervised approaches directly leverage weakly annotated web images in the joint embedding learning framework. The objective of these approaches would suffer significantly when the ratio of noisy and missing tags associated with the web images is very high. In this regard, we propose a CP decomposition based tensor completion framework to refine the tags of web images by modeling observed ternary inter-relations between the sets of labeled images, tags, and web images as a tensor. To effectively deal with the high ratio of missing entries likely in our case, we incorporate intra-modal correlation as side information in the proposed framework. Our tag refinement approach combined with existing web supervised image-text embedding approaches provide a more principled way for learning the joint embedding models in the presence of significant noise from web data and limited clean labeled data. Experiments on benchmark datasets demonstrate that the proposed approach helps to achieve a significant performance gain in image-text retrieval.

Using Scene Graphs for Detecting Visual Relationships

Anurag Tripathi, Siddharth Srivastava, Brejesh Lall, Santanu Chaudhury

Responsive image

Auto-TLDR; Relationship Detection using Context Aligned Scene Graph Embeddings

Slides Poster Similar

In this paper we solve the problem of detecting relationships between pairs of objects in an image. We develop spatially aware word embeddings using scene graphs and use joint feature representations containing visual, spatial and semantic embeddings from the input images to train a deep network on the task of relationship detection. Further, we propose to utilize context aligned scene graph embeddings from the train set, without requiring explicit availability of scene graphs at test time. We show that the proposed method outperforms the state-of-the-art methods for predicate detection and provides competing results on relationship detection. We also show the generalization ability of the proposed method by performing predictions under zero shot settings. Further, we also provide an exhaustive empirical evaluation on each component of the proposed network.

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.

Transformer Reasoning Network for Image-Text Matching and Retrieval

Nicola Messina, Fabrizio Falchi, Andrea Esuli, Giuseppe Amato

Responsive image

Auto-TLDR; A Transformer Encoder Reasoning Network for Image-Text Matching in Large-Scale Information Retrieval

Slides Poster Similar

Image-text matching is an interesting and fascinating task in modern AI research. Despite the evolution of deep-learning-based image and text processing systems, multi-modal matching remains a challenging problem. In this work, we consider the problem of accurate image-text matching for the task of multi-modal large-scale information retrieval. State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms. However, this invalidates any chance to extract separate visual and textual features needed for later indexing steps in large-scale retrieval systems. In this regard, we introduce the Transformer Encoder Reasoning Network (TERN), an architecture built upon one of the modern relationship-aware self-attentive architectures, the Transformer Encoder (TE). This architecture is able to separately reason on the two different modalities and to enforce a final common abstract concept space by sharing the weights of the deeper transformer layers. Thanks to this design, the implemented network is able to produce compact and very rich visual and textual features available for the successive indexing step. Experiments are conducted on the MS-COCO dataset, and we evaluate the results using a discounted cumulative gain metric with relevance computed exploiting caption similarities, in order to assess possibly non-exact but relevant search results. We demonstrate that on this metric we are able to achieve state-of-the-art results in the image retrieval task. Our code is freely available at https://github.com/mesnico/TERN.

Enriching Video Captions with Contextual Text

Philipp Rimle, Pelin Dogan, Markus Gross

Responsive image

Auto-TLDR; Contextualized Video Captioning Using Contextual Text

Slides Poster Similar

Understanding video content and generating caption with context is an important and challenging task. Unlike prior methods that typically attempt to generate generic video captions without context, our architecture contextualizes captioning by infusing extracted information from relevant text data. We propose an end-to-end sequence-to-sequence model which generates video captions based on visual input, and mines relevant knowledge such as names and locations from contextual text. In contrast to previous approaches, we do not preprocess the text further, and let the model directly learn to attend over it. Guided by the visual input, the model is able to copy words from the contextual text via a pointer-generator network, allowing to produce more specific video captions. We show competitive performance on the News Video Dataset and, through ablation studies, validate the efficacy of contextual video captioning as well as individual design choices in our model architecture.

Making Every Label Count: Handling Semantic Imprecision by Integrating Domain Knowledge

Clemens-Alexander Brust, Björn Barz, Joachim Denzler

Responsive image

Auto-TLDR; Class Hierarchies for Imprecise Label Learning and Annotation eXtrapolation

Slides Poster Similar

Noisy data, crawled from the web or supplied by volunteers such as Mechanical Turkers or citizen scientists, is considered an alternative to professionally labeled data. There has been research focused on mitigating the effects of label noise. It is typically modeled as inaccuracy, where the correct label is replaced by an incorrect label from the same set. We consider an additional dimension of label noise: imprecision. For example, a non-breeding snow bunting is labeled as a bird. This label is correct, but not as precise as the task requires. Standard softmax classifiers cannot learn from such a weak label because they consider all classes mutually exclusive, which non-breeding snow bunting and bird are not. We propose CHILLAX (Class Hierarchies for Imprecise Label Learning and Annotation eXtrapolation), a method based on hierarchical classification, to fully utilize labels of any precision. Experiments on noisy variants of NABirds and ILSVRC2012 show that our method outperforms strong baselines by as much as 16.4 percentage points, and the current state of the art by up to 3.9 percentage points.

Attentive Visual Semantic Specialized Network for Video Captioning

Jesus Perez-Martin, Benjamin Bustos, Jorge Pérez

Responsive image

Auto-TLDR; Adaptive Visual Semantic Specialized Network for Video Captioning

Slides Poster Similar

As an essential high-level task of video understanding topic, automatically describing a video with natural language has recently gained attention as a fundamental challenge in computer vision. Previous models for video captioning have several limitations, such as the existence of gaps in current semantic representations and the inexpressibility of the generated captions. To deal with these limitations, in this paper, we present a new architecture that we callAttentive Visual Semantic Specialized Network(AVSSN), which is an encoder-decoder model based on our Adaptive Attention Gate and Specialized LSTM layers. This architecture can selectively decide when to use visual or semantic information into the text generation process. The adaptive gate makes the decoder to automatically select the relevant information for providing a better temporal state representation than the existing decoders. Besides, the model is capable of learning to improve the expressiveness of generated captions attending to their length, using a sentence-length-related loss function. We evaluate the effectiveness of the proposed approach on the Microsoft Video Description(MSVD) and the Microsoft Research Video-to-Text (MSR-VTT) datasets, achieving state-of-the-art performance with several popular evaluation metrics: BLEU-4, METEOR, CIDEr, and ROUGE_L.

A Novel Attention-Based Aggregation Function to Combine Vision and Language

Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Responsive image

Auto-TLDR; Fully-Attentive Reduction for Vision and Language

Slides Poster Similar

The joint understanding of vision and language has been recently gaining a lot of attention in both the Computer Vision and Natural Language Processing communities, with the emergence of tasks such as image captioning, image-text matching, and visual question answering. As both images and text can be encoded as sets or sequences of elements - like regions and words - proper reduction functions are needed to transform a set of encoded elements into a single response, like a classification or similarity score. In this paper, we propose a novel fully-attentive reduction method for vision and language. Specifically, our approach computes a set of scores for each element of each modality employing a novel variant of cross-attention, and performs a learnable and cross-modal reduction, which can be used for both classification and ranking. We test our approach on image-text matching and visual question answering, building fair comparisons with other reduction choices, on both COCO and VQA 2.0 datasets. Experimentally, we demonstrate that our approach leads to a performance increase on both tasks. Further, we conduct ablation studies to validate the role of each component of the approach.

MEG: Multi-Evidence GNN for Multimodal Semantic Forensics

Ekraam Sabir, Ayush Jaiswal, Wael Abdalmageed, Prem Natarajan

Responsive image

Auto-TLDR; Scalable Image Repurposing Detection with Graph Neural Network Based Model

Slides Poster Similar

Image repurposing is a category of fake news where a digitally unmanipulated image is misrepresented by means of its accompanying metadata such as captions, location, etc., where the image and accompanying metadata together comprise a multimedia package. The problem setup is to authenticate a query multimedia package using a reference dataset of potentially related packages as evidences. Existing methods are limited to using a single evidence (retrieved package), which ignores potential performance improvement from the use of multiple evidences. In this work, we introduce a novel graph neural network based model for image repurposing detection, which effectively utilizes multiple retrieved packages as evidences and is scalable with the number of evidences. We compare the scalability and performance of our model against existing methods. Experimental results show that the proposed model outperforms existing state-of-the-art for image repurposing detection with an error reduction of up to 25%.

More Correlations Better Performance: Fully Associative Networks for Multi-Label Image Classification

Yaning Li, Liu Yang

Responsive image

Auto-TLDR; Fully Associative Network for Fully Exploiting Correlation Information in Multi-Label Classification

Slides Poster Similar

Recent researches demonstrate that correlation modeling plays a key role in high-performance multi-label classification methods. However, existing methods do not take full advantage of correlation information, especially correlations in feature and label spaces of each image, which limits the performance of correlation-based multi-label classification methods. With more correlations considered, in this study, a Fully Associative Network (FAN) is proposed for fully exploiting correlation information, which involves both visual feature and label correlations. Specifically, FAN introduces a robust covariance pooling to summarize convolution features as global image representation for capturing feature correlation in the multi-label task. Moreover, it constructs an effective label correlation matrix based on a re-weighted scheme, which is fed into a graph convolution network for capturing label correlation. Then, correlation between covariance representations (i.e., feature correlation ) and the outputs of GCN (i.e., label correlation) are modeled for final prediction. Experimental results on two datasets illustrate the effectiveness and efficiency of our proposed FAN compared with state-of-the-art methods.

Picture-To-Amount (PITA): Predicting Relative Ingredient Amounts from Food Images

Jiatong Li, Fangda Han, Ricardo Guerrero, Vladimir Pavlovic

Responsive image

Auto-TLDR; PITA: A Deep Learning Architecture for Predicting the Relative Amount of Ingredients from Food Images

Slides Poster Similar

Increased awareness of the impact of food consumption on health and lifestyle today has given rise to novel data-driven food analysis systems. Although these systems may recognize the ingredients, a detailed analysis of their amounts in the meal, which is paramount for estimating the correct nutrition, is usually ignored. In this paper, we study the novel and challenging problem of predicting the relative amount of each ingredient from a food image. We propose PITA, the Picture-to-Amount deep learning architecture to solve the problem. More specifically, we predict the ingredient amounts using a domain-driven Wasserstein loss from image-to-recipe cross-modal embeddings learned to align the two views of food data. Experiments on a dataset of recipes collected from the Internet show the model generates promising results and improves the baselines on this challenging task.

Multimodal Side-Tuning for Document Classification

Stefano Zingaro, Giuseppe Lisanti, Maurizio Gabbrielli

Responsive image

Auto-TLDR; Side-tuning for Multimodal Document Classification

Slides Poster Similar

In this paper, we propose to exploit the side-tuning framework for multimodal document classification. Side-tuning is a methodology for network adaptation recently introduced to solve some of the problems related to previous approaches. Thanks to this technique it is actually possible to overcome model rigidity and catastrophic forgetting of transfer learning by fine-tuning. The proposed solution uses off-the-shelf deep learning architectures leveraging the side-tuning framework to combine a base model with a tandem of two side networks. We show that side-tuning can be successfully employed also when different data sources are considered, e.g. text and images in document classification. The experimental results show that this approach pushes further the limit for document classification accuracy with respect to the state of the art.

PrivAttNet: Predicting Privacy Risks in Images Using Visual Attention

Chen Zhang, Thivya Kandappu, Vigneshwaran Subbaraju

Responsive image

Auto-TLDR; PrivAttNet: A Visual Attention Based Approach for Privacy Sensitivity in Images

Slides Poster Similar

Visual privacy concerns associated with image sharing is a critical issue that need to be addressed to enable safe and lawful use of online social platforms. Users of social media platforms often suffer from no guidance in sharing sensitive images in public, and often face with social and legal consequences. Given the recent success of visual attention based deep learning methods in measuring abstract phenomena like image memorability, we are motivated to investigate whether visual attention based methods could be useful in measuring psycho-physical phenomena like "privacy sensitivity". In this paper we propose PrivAttNet -- a visual attention based approach, that can be trained end-to-end to estimate the privacy sensitivity of images without explicitly detecting objects and attributes present in the image. We show that our PrivAttNet model outperforms various SOTA and baseline strategies -- a 1.6 fold reduction in $L1-error$ over SOTA and 7%--10% improvement in Spearman-rank correlation between the predicted and ground truth sensitivity scores. Additionally, the attention maps from PrivAttNet are found to be useful in directing the users to the regions that are responsible for generating the privacy risk score.

Dual Path Multi-Modal High-Order Features for Textual Content Based Visual Question Answering

Yanan Li, Yuetan Lin, Hongrui Zhao, Donghui Wang

Responsive image

Auto-TLDR; TextVQA: An End-to-End Visual Question Answering Model for Text-Based VQA

Slides Similar

As a typical cross-modal problem, visual question answering (VQA) has received increasing attention from the communities of computer vision and natural language processing. Reading and reasoning about texts and visual contents in the images is a burgeoning and important research topic in VQA, especially for the visually impaired assistance applications. Given an image, it aims to predict an answer to a provided natural language question closely related to its textual contents. In this paper, we propose a novel end-to-end textual content based VQA model, which grounds question answering both on the visual and textual information. After encoding the image, question and recognized text words, it uses multi-modal factorized high-order modules and the attention mechanism to fuse question-image and question-text features respectively. The complex correlations among different features can be captured efficiently. To ensure the model's extendibility, it embeds candidate answers and recognized texts in a semantic embedding space and adopts semantic embedding based classifier to perform answer prediction. Extensive experiments on the newly proposed benchmark TextVQA demonstrate that the proposed model can achieve promising results.

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.

Deep Convolutional Embedding for Digitized Painting Clustering

Giovanna Castellano, Gennaro Vessio

Responsive image

Auto-TLDR; A Deep Convolutional Embedding Model for Clustering Artworks

Slides Poster Similar

Clustering artworks is difficult because of several reasons. On one hand, recognizing meaningful patterns in accordance with domain knowledge and visual perception is extremely hard. On the other hand, the application of traditional clustering and feature reduction techniques to the highly dimensional pixel space can be ineffective. To address these issues, we propose to use a deep convolutional embedding model for digitized painting clustering, in which the task of mapping the input raw data to an abstract, latent space is jointly optimized with the task of finding a set of cluster centroids in this latent feature space. Quantitative and qualitative experimental results show the effectiveness of the proposed method. The model is also able to outperform other state-of-the-art deep clustering approaches to the same problem. The proposed method may be beneficial to several art-related tasks, particularly visual link retrieval and historical knowledge discovery in painting datasets.

MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level

Amar Shrestha, Krittaphat Pugdeethosapol, Haowen Fang, Qinru Qiu

Responsive image

Auto-TLDR; MAGNet: A Multi-Region Attention-Aware Grounding Network for Free-form Textual Queries

Slides Poster Similar

Grounding free-form textual queries necessitates an understanding of these textual phrases and its relation to the visual cues to reliably reason about the described locations. Spatial attention networks are known to learn this relationship and focus its gaze on salient objects in the image. Thus, we propose to utilize spatial attention networks for image-level visual-textual fusion preserving local (word) and global (phrase) information to refine region proposals with an in-network Region Proposal Network (RPN) and detect single or multiple regions for a phrase query. We focus only on the phrase query - ground truth pair (referring expression) for a model independent of the constraints of the datasets i.e. additional attributes, context etc. For such referring expression dataset ReferIt game, our Multi- region Attention-assisted Grounding network (MAGNet) achieves over 12% improvement over the state-of-the-art. Without the con- text from image captions and attribute information in Flickr30k Entities, we still achieve competitive results compared to the state- of-the-art.

Force Banner for the Recognition of Spatial Relations

Robin Deléarde, Camille Kurtz, Laurent Wendling, Philippe Dejean

Responsive image

Auto-TLDR; Spatial Relation Recognition using Force Banners

Slides Similar

Studying the spatial organization of objects in images is fundamental to increase both the understanding of the sensed scene and the accuracy of the perceived similarity between images. This often leads to the problem of spatial relation recognition: given two objects depicted in an image, what is their spatial relation? In this article, we consider this as a classification problem. Instead of considering directly the original image space (or imaging features) to predict the spatial relation, we propose a novel intermediate representation (called Force Banner) modeling rich spatial information between pairs of objects composing a scene. Such a representation captures the relative position between objects using a panel of forces (attraction and repulsion), that take into account the structural shapes of the objects and their distance in a directional fashion. Force Banners are used to feed a classical 2D Convolutional Neural Network (CNN) for the recognition of spatial relations, benefiting from pre-trained models and fine-tuning. Experimental results obtained on a dataset of images with various shapes highlight the interest of this approach, and in particular its benefit to describe spatial information.

Visual Oriented Encoder: Integrating Multimodal and Multi-Scale Contexts for Video Captioning

Bang Yang, Yuexian Zou

Responsive image

Auto-TLDR; Visual Oriented Encoder for Video Captioning

Slides Poster Similar

Video captioning is a challenging task which aims at automatically generating a natural language description of a given video. Recent researches have shown that exploiting the intrinsic multi-modalities of videos significantly promotes captioning performance. However, how to integrate multi-modalities to generate effective semantic representations for video captioning is still an open issue. Some researchers proposed to learn multimodal features in parallel during the encoding stage. The downside of these methods lies in the neglect of the interaction among multi-modalities and their rich contextual information. In this study, inspired by the fact that visual contents are generally more important for comprehending videos, we propose a novel Visual Oriented Encoder (VOE) to integrate multimodal features in an interactive manner. Specifically, VOE is designed as a hierarchical structure, where bottom layers are utilized to extract multi-scale contexts from auxiliary modalities while the top layer is exploited to generate joint representations by considering both visual and contextual information. Following the encoder-decoder framework, we systematically develop a VOE-LSTM model and evaluate it on two mainstream benchmarks: MSVD and MSR-VTT. Experimental results show that the proposed VOE surpasses conventional encoders and our VOE-LSTM model achieves competitive results compared with state-of-the-art approaches.

VSB^2-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Hashing

Xin Li, Xiangfeng Wang, Bo Jin, Wenjie Zhang, Jun Wang, Hongyuan Zha

Responsive image

Auto-TLDR; VSB^2-Net: inductive zero-shot hashing for image retrieval

Slides Poster Similar

Zero-shot hashing aims at learning hashing model from seen classes and the obtained model is capable of generalizing to unseen classes for image retrieval. Inspired by zero-shot learning, existing zero-shot hashing methods usually transfer the supervised knowledge from seen to unseen classes, by embedding the hamming space to a shared semantic space. However, this makes instances difficult to distinguish due to limited hashing bit numbers, especially for semantically similar unseen classes. We propose a novel inductive zero-shot hashing framework, i.e., VSB^2-Net, where both semantic space and visual feature space are embedded to the same hamming space instead. The reconstructive semantic relationships are established in the hamming space, preserving local similarity relationships and explicitly enlarging the discrepancy between semantic hamming vectors. A two-task architecture, comprising of classification module and visual feature reconstruction module, is employed to enhance the generalization and transfer abilities. Extensive evaluation results on several benchmark datasets demonstratethe superiority of our proposed method compared to several state-of-the-art baselines.

Context Visual Information-Based Deliberation Network for Video Captioning

Min Lu, Xueyong Li, Caihua Liu

Responsive image

Auto-TLDR; Context visual information-based deliberation network for video captioning

Slides Poster Similar

Video captioning is to automatically and accurately generate a textual description for a video. The typical methods following the encoder-decoder architecture directly utilized hidden states to predict words. Nevertheless, these methods did not amend the inaccurate hidden states before feeding those states into word prediction. This led to a cascade of errors on generating word by word. In this paper, the context visual information-based deliberation network is proposed, abbreviated as CVI-DelNet. Its key idea is to introduce the deliberator into the encoder-decoder framework. The encoder-decoder firstly generates a raw hidden state sequence. Unlike the existing methods, the raw hidden state is no more directly used for word prediction but is fed into the deliberator to generate the refined hidden state. The words are then predicted according to the refined hidden states and the contextual visual features. Results on two datasets shows that the proposed method significantly outperforms the baselines.

Generalized Local Attention Pooling for Deep Metric Learning

Carlos Roig Mari, David Varas, Issey Masuda, Juan Carlos Riveiro, Elisenda Bou-Balust

Responsive image

Auto-TLDR; Generalized Local Attention Pooling for Deep Metric Learning

Slides Poster Similar

Deep metric learning has been key to recent advances in face verification and image retrieval amongst others. These systems consist on a feature extraction block (extracts feature maps from images) followed by a spatial dimensionality reduction block (generates compact image representations from the feature maps) and an embedding generation module (projects the image representation to the embedding space). While research on deep metric learning has focused on improving the losses for the embedding generation module, the dimensionality reduction block has been overlooked. In this work, we propose a novel method to generate compact image representations which uses local spatial information through an attention mechanism, named Generalized Local Attention Pooling (GLAP). This method, instead of being placed at the end layer of the backbone, is connected at an intermediate level, resulting in lower memory requirements. We assess the performance of the aforementioned method by comparing it with multiple dimensionality reduction techniques, demonstrating the importance of using attention weights to generate robust compact image representations. Moreover, we compare the performance of multiple state-of-the-art losses using the standard deep metric learning system against the same experiment with our GLAP. Experiments showcase that the proposed Generalized Local Attention Pooling mechanism outperforms other pooling methods when compared with current state-of-the-art losses for deep metric learning.

Leveraging Quadratic Spherical Mutual Information Hashing for Fast Image Retrieval

Nikolaos Passalis, Anastasios Tefas

Responsive image

Auto-TLDR; Quadratic Mutual Information for Large-Scale Hashing and Information Retrieval

Slides Poster Similar

Several deep supervised hashing techniques have been proposed to allow for querying large image databases. However, it is often overlooked that the process of information retrieval can be modeled using information-theoretic metrics, leading to optimizing various proxies for the problem at hand instead. Contrary to this, we propose a deep supervised hashing algorithm that optimizes the learned codes using an information-theoretic measure, the Quadratic Mutual Information (QMI). The proposed method is adapted to the needs of large-scale hashing and information retrieval leading to a novel information-theoretic measure, the Quadratic Spherical Mutual Information (QSMI), that is inspired by QMI, but leads to significant better retrieval precision. Indeed, the effectiveness of the proposed method is demonstrated under several different scenarios, using different datasets and network architectures, outperforming existing deep supervised image hashing techniques.

Hierarchical Multimodal Attention for Deep Video Summarization

Melissa Sanabria, Frederic Precioso, Thomas Menguy

Responsive image

Auto-TLDR; Automatic Summarization of Professional Soccer Matches Using Event-Stream Data and Multi- Instance Learning

Slides Poster Similar

The way people consume sports on TV has drastically evolved in the last years, particularly under the combined effects of the legalization of sport betting and the huge increase of sport analytics. Several companies are nowadays sending observers in the stadiums to collect live data of all the events happening on the field during the match. Those data contain meaningful information providing a very detailed description of all the actions occurring during the match to feed the coaches and staff, the fans, the viewers, and the gamblers. Exploiting all these data, sport broadcasters want to generate extra content such as match highlights, match summaries, players and teams analytics, etc., to appeal subscribers. This paper explores the problem of summarizing professional soccer matches as automatically as possible using both the aforementioned event-stream data collected from the field and the content broadcasted on TV. We have designed an architecture, introducing first (1) a Multiple Instance Learning method that takes into account the sequential dependency among events and then (2) a hierarchical multimodal attention layer that grasps the importance of each event in an action. We evaluate our approach on matches from two professional European soccer leagues, showing its capability to identify the best actions for automatic summarization by comparing with real summaries made by human operators.

GCNs-Based Context-Aware Short Text Similarity Model

Xiaoqi Sun

Responsive image

Auto-TLDR; Context-Aware Graph Convolutional Network for Text Similarity

Slides Poster Similar

Semantic textual similarity is a fundamental task in text mining and natural language processing (NLP), which has profound research value. The essential step for text similarity is text representation learning. Recently, researches have explored the graph convolutional network (GCN) techniques on text representation, since GCN does well in handling complex structures and preserving syntactic information. However, current GCN models are usually limited to very shallow layers due to the vanishing gradient problem, which cannot capture non-local dependency information of sentences. In this paper, we propose a GCNs-based context-aware (GCSTS) model that applies iterated GCN blocks to train deeper GCNs. Recurrently employing the same GCN block prevents over-fitting and provides broad effective input width. Combined with dense connections, GCSTS can be trained more deeply. Besides, we use dynamic graph structures in the block, which further extend the receptive field of each vertex in graphs, learning better sentence representations. Experiments show that our model outperforms existing models on several text similarity datasets, while also verify that GCNs-based text representation models can be trained in a deeper manner, rather than being trained in two or three layers.

Self-Supervised Joint Encoding of Motion and Appearance for First Person Action Recognition

Mirco Planamente, Andrea Bottino, Barbara Caputo

Responsive image

Auto-TLDR; A Single Stream Architecture for Egocentric Action Recognition from the First-Person Point of View

Slides Poster Similar

Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from the first-person point of view. An open challenge in egocentric action recognition is that videos lack detailed information about the main actor's pose and thus tend to record only parts of the movement when focusing on manipulation tasks. Thus, the amount of information about the action itself is limited, making crucial the understanding of the manipulated objects and their context. Many previous works addressed this issue with two-stream architectures, where one stream is dedicated to modeling the appearance of objects involved in the action, and another to extracting motion features from optical flow. In this paper, we argue that learning features jointly from these two information channels is beneficial to capture the spatio-temporal correlations between the two better. To this end, we propose a single stream architecture able to do so, thanks to the addition of a self-supervised block that uses a pretext motion prediction task to intertwine motion and appearance knowledge. Experiments on several publicly available databases show the power of our approach.

Learning Natural Thresholds for Image Ranking

Somayeh Keshavarz, Quang Nhat Tran, Richard Souvenir

Responsive image

Auto-TLDR; Image Representation Learning and Label Discretization for Natural Image Ranking

Slides Poster Similar

For image ranking tasks with naturally continuous output, such as age and scenicness estimation, it is common to discretize the label range and apply methods from (ordered) classification analysis. In this paper, we propose a data-driven approach for simultaneous representation learning and label discretization. Compared to arbitrarily selecting thresholds, we seek to learn thresholds and image representations by minimizing a novel loss function in an end-to-end model. We demonstrate our combined approach on a variety of image ranking tasks and demonstrate that it outperforms task-specific methods. Additionally, our learned partitioning scheme can be transferred to improve methods that rely on discretization.

Text Synopsis Generation for Egocentric Videos

Aidean Sharghi, Niels Lobo, Mubarak Shah

Responsive image

Auto-TLDR; Egocentric Video Summarization Using Multi-task Learning for End-to-End Learning

Slides Similar

Mass utilization of body-worn cameras has led to a huge corpus of available egocentric video. Existing video summarization algorithms can accelerate browsing such videos by selecting (visually) interesting shots from them. Nonetheless, since the system user still has to watch the summary videos, browsing large video databases remain a challenge. Hence, in this work, we propose to generate a textual synopsis, consisting of a few sentences describing the most important events in a long egocentric videos. Users can read the short text to gain insight about the video, and more importantly, efficiently search through the content of a large video database using text queries. Since egocentric videos are long and contain many activities and events, using video-to-text algorithms results in thousands of descriptions, many of which are incorrect. Therefore, we propose a multi-task learning scheme to simultaneously generate descriptions for video segments and summarize the resulting descriptions in an end-to-end fashion. We Input a set of video shots and the network generates a text description for each shot. Next, visual-language content matching unit that is trained with a weakly supervised objective, identifies the correct descriptions. Finally, the last component of our network, called purport network, evaluates the descriptions all together to select the ones containing crucial information. Out of thousands of descriptions generated for the video, a few informative sentences are returned to the user. We validate our framework on the challenging UT Egocentric video dataset, where each video is between 3 to 5 hours long, associated with over 3000 textual descriptions on average. The generated textual summaries, including only 5 percent (or less) of the generated descriptions, are compared to groundtruth summaries in text domain using well-established metrics in natural language processing.

Multi-Level Deep Learning Vehicle Re-Identification Using Ranked-Based Loss Functions

Eleni Kamenou, Jesus Martinez-Del-Rincon, Paul Miller, Patricia Devlin - Hill

Responsive image

Auto-TLDR; Multi-Level Re-identification Network for Vehicle Re-Identification

Slides Poster Similar

Identifying vehicles across a network of cameras with non-overlapping fields of view remains a challenging research problem due to scene occlusions, significant inter-class similarity and intra-class variability. In this paper, we propose an end-to-end multi-level re-identification network that is capable of successfully projecting same identity vehicles closer to one another in the embedding space, compared to vehicles of different identities. Robust feature representations are obtained by combining features at multiple levels of the network. As for the learning process, we employ a recent state-of-the-art structured metric learning loss function previously applied to other retrieval problems and adjust it to the vehicle re-identification task. Furthermore, we explore the cases of image-to-image, image-to-video and video-to-video similarity metric. Finally, we evaluate our system and achieve great performance on two large-scale publicly available datasets, CityFlow-ReID and VeRi-776. Compared to most existing state-of-art approaches, our approach is simpler and more straightforward, utilizing only identity-level annotations, while avoiding post-processing the ranking results (re-ranking) at the testing phase.

Semantics to Space(S2S): Embedding Semantics into Spatial Space for Zero-Shot Verb-Object Query Inferencing

Sungmin Eum, Heesung Kwon

Responsive image

Auto-TLDR; Semantics-to-Space: Deep Zero-Shot Learning for Verb-Object Interaction with Vectors

Slides Poster Similar

We present a novel deep zero-shot learning (ZSL) model for inferencing human-object-interaction with verb-object (VO) query. While the previous two-stream ZSL approaches only use the semantic/textual information to be fed into the query stream, we seek to incorporate and embed the semantics into the visual representation stream as well. Our approach is powered by Semantics-to-Space (S2S) architecture where semantics derived from the residing objects are embedded into a spatial space of the visual stream. This architecture allows the co-capturing of the semantic attributes of the human and the objects along with their location/size/silhouette information. To validate, we have constructed a new dataset, Verb-Transferability 60 (VT60). VT60 provides 60 different VO pairs with overlapping verbs tailored for testing two-stream ZSL approaches with VO query. Experimental evaluations show that our approach not only outperforms the state-of-the-art, but also shows the capability of consistently improving performance regardless of which ZSL baseline architecture is used.

Transformer Networks for Trajectory Forecasting

Francesco Giuliari, Hasan Irtiza, Marco Cristani, Fabio Galasso

Responsive image

Auto-TLDR; TransformerNetworks for Trajectory Prediction of People Interactions

Slides Poster Similar

Most recent successes on forecasting the people mo-tion are based on LSTM models andallmost recent progress hasbeen achieved by modelling the social interaction among peopleand the people interaction with the scene. We question the useof the LSTM models and propose the novel use of TransformerNetworks for trajectory forecasting. This is a fundamental switchfrom the sequential step-by-step processing of LSTMs to theonly-attention-based memory mechanisms of Transformers. Inparticular, we consider both the original Transformer Network(TF) and the larger Bidirectional Transformer (BERT), state-of-the-art on all natural language processing tasks. Our proposedTransformers predict the trajectories of the individual peoplein the scene. These are “simple” models because each personis modelled separately without any complex human-human norscene interaction terms. In particular, the TF modelwithoutbells and whistlesyields the best score on the largest and mostchallenging trajectory forecasting benchmark of TrajNet [1]. Ad-ditionally, its extension which predicts multiple plausible futuretrajectories performs on par with more engineered techniqueson the 5 datasets of ETH [2]+UCY [3]. Finally, we showthat Transformers may deal with missing observations, as itmay be the case with real sensor data. Code is available atgithub.com/FGiuliari/Trajectory-Transformer

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.

The Color Out of Space: Learning Self-Supervised Representations for Earth Observation Imagery

Stefano Vincenzi, Angelo Porrello, Pietro Buzzega, Marco Cipriano, Pietro Fronte, Roberto Cuccu, Carla Ippoliti, Annamaria Conte, Simone Calderara

Responsive image

Auto-TLDR; Satellite Image Representation Learning for Remote Sensing

Slides Poster Similar

The recent growth in the number of satellite images fosters the development of effective deep-learning techniques for Remote Sensing (RS). However, their full potential is untapped due to the lack of large annotated datasets. Such a problem is usually countered by fine-tuning a feature extractor that is previously trained on the ImageNet dataset. Unfortunately, the domain of natural images differs from the RS one, which hinders the final performance. In this work, we propose to learn meaningful representations from satellite imagery, leveraging its high-dimensionality spectral bands to reconstruct the visible colors. We conduct experiments on land cover classification (BigEarthNet) and West Nile Virus detection, showing that colorization is a solid pretext task for training a feature extractor. Furthermore, we qualitatively observe that guesses based on natural images and colorization rely on different parts of the input. This paves the way to an ensemble model that eventually outperforms both the above-mentioned techniques.

Attention-Based Deep Metric Learning for Near-Duplicate Video Retrieval

Kuan-Hsun Wang, Chia Chun Cheng, Yi-Ling Chen, Yale Song, Shang-Hong Lai

Responsive image

Auto-TLDR; Attention-based Deep Metric Learning for Near-duplicate Video Retrieval

Slides Similar

Near-duplicate video retrieval (NDVR) is an important and challenging problem due to the increasing amount of videos uploaded to the Internet. In this paper, we propose an attention-based deep metric learning method for NDVR. Our method is based on well-established principles: We leverage two-stream networks to combine RGB and optical flow features, and incorporate an attention module to effectively deal with distractor frames commonly observed in near duplicate videos. We further aggregate the features corresponding to multiple video segments to enhance the discriminative power. The whole system is trained using a deep metric learning objective with a Siamese architecture. Our experiments show that the attention module helps eliminate redundant and noisy frames, while focusing on visually relevant frames for solving NVDR. We evaluate our approach on recent large-scale NDVR datasets, CC_WEB_VIDEO, VCDB, FIVR and SVD. To demonstrate the generalization ability of our approach, we report results in both within- and cross-dataset settings, and show that the proposed method significantly outperforms state-of-the-art approaches.

RMS-Net: Regression and Masking for Soccer Event Spotting

Matteo Tomei, Lorenzo Baraldi, Simone Calderara, Simone Bronzin, Rita Cucchiara

Responsive image

Auto-TLDR; An Action Spotting Network for Soccer Videos

Slides Poster Similar

The recently proposed action spotting task consists in finding the exact timestamp in which an event occurs. This task fits particularly well for soccer videos, where events correspond to salient actions strictly defined by soccer rules (a goal occurs when the ball crosses the goal line). In this paper, we devise a lightweight and modular network for action spotting, which can simultaneously predict the event label and its temporal offset using the same underlying features. We enrich our model with two training strategies: the first one for data balancing and uniform sampling, the second for masking ambiguous frames and keeping the most discriminative visual cues. When tested on the SoccerNet dataset and using standard features, our full proposal exceeds the current state of the art by 3 Average-mAP points. Additionally, it reaches a gain of more than 10 Average-mAP points on the test set when fine-tuned in combination with a strong 2D backbone.

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.

Multi-Modal Deep Clustering: Unsupervised Partitioning of Images

Guy Shiran, Daphna Weinshall

Responsive image

Auto-TLDR; Multi-Modal Deep Clustering for Unlabeled Images

Slides Poster Similar

The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an end-to-end fashion, providing direct cluster assignments of images without additional processing. Multi-Modal Deep Clustering (MMDC), trains a deep network to align its image embeddings with target points sampled from a Gaussian Mixture Model distribution. The cluster assignments are then determined by mixture component association of image embeddings. Simultaneously, the same deep network is trained to solve an additional self-supervised task. This pushes the network to learn more meaningful image representations and stabilizes the training. Experimental results show that MMDC achieves or exceeds state-of-the-art performance on four challenging benchmarks. On natural image datasets we improve on previous results with significant margins of up to 11% absolute accuracy points, yielding an accuracy of 70% on CIFAR-10 and 61% on STL-10.

Hybrid Decomposition Convolution Neural Network and Vocabulary Forest for Image Retrieval

Djenouri Youcef, Jon Hjelmervik

Responsive image

Auto-TLDR; DCNN-vForest: Convolutional Neural Network and Vocabulary Forest for Efficient Image Retrieval

Slides Poster Similar

This paper introduces a highly efficient image retrieval technique called DCNN-vForest (Decomposition Convolution Neural Network and vocabulary Forest), which aims to retrieve the relevant images to the given image query by studying the correlation between images in the image database based on decomposition. The regional and global features of the image database are first extracted using the convolution neural network, and then divided into similar clusters using the Kmeans algorithm. We propose a new structure called vForest (vocabulary Forest), by calculating the vocabulary tree on each cluster of images. The retrieval process benefits from the knowledge provided by the vForest, and instead of considering the whole image database, only the most similar clusters to the image query are explored. To demonstrate the usefulness of our approach, intensive experiments have been carried out on ground-truth image databases, the results reveal the superiority of DCNN-vForest against the baseline image retrieval solutions, in terms of runtime and accuracy.

Label Incorporated Graph Neural Networks for Text Classification

Yuan Xin, Linli Xu, Junliang Guo, Jiquan Li, Xin Sheng, Yuanyuan Zhou

Responsive image

Auto-TLDR; Graph Neural Networks for Semi-supervised Text Classification

Slides Poster Similar

Graph Neural Networks (GNNs) have achieved great success on graph-structured data, and their applications on traditional data structures such as natural language processing and semi-supervised text classification have been extensively explored in recent years. While previous works only consider the text information while building the graph, heterogeneous information such as labels is ignored. In this paper, we consider to incorporate the label information while building the graph by adding text-label-text paths, through which the supervision information will propagate among the graph more directly. Specifically, we treat labels as nodes in the graph which also contains text and word nodes, and then connect labels with texts belonging to that label. Through graph convolutions, label embeddings are jointly learned with text embeddings in the same latent semantic space. The newly incorporated label nodes will facilitate learning more accurate text embeddings by introducing the label information, and thus benefit the downstream text classification tasks. Extensive results on several benchmark datasets show that the proposed framework outperforms baseline methods by a significant margin.

GuCNet: A Guided Clustering-Based Network for Improved Classification

Ushasi Chaudhuri, Syomantak Chaudhuri, Subhasis Chaudhuri

Responsive image

Auto-TLDR; Semantic Classification of Challenging Dataset Using Guide Datasets

Slides Poster Similar

We deal with the problem of semantic classification of challenging and highly-cluttered dataset. We present a novel, and yet a very simple classification technique by leveraging the ease of classifiability of any existing well separable dataset for guidance. Since the guide dataset which may or may not have any semantic relationship with the experimental dataset, forms well separable clusters in the feature set, the proposed network tries to embed class-wise features of the challenging dataset to those distinct clusters of the guide set, making them more separable. Depending on the availability, we propose two types of guide sets: one using texture (image) guides and another using prototype vectors representing cluster centers. Experimental results obtained on the challenging benchmark RSSCN, LSUN, and TU-Berlin datasets establish the efficacy of the proposed method as we outperform the existing state-of-the-art techniques by a considerable margin.

Detective: An Attentive Recurrent Model for Sparse Object Detection

Amine Kechaou, Manuel Martinez, Monica Haurilet, Rainer Stiefelhagen

Responsive image

Auto-TLDR; Detective: An attentive object detector that identifies objects in images in a sequential manner

Slides Poster Similar

In this work, we present Detective – an attentive object detector that identifies objects in images in a sequential manner. Our network is based on an encoder-decoder architecture, where the encoder is a convolutional neural network, and the decoder is a convolutional recurrent neural network coupled with an attention mechanism. At each iteration, our decoder focuses on the relevant parts of the image using an attention mechanism, and then estimates the object’s class and the bounding box coordinates. Current object detection models generate dense predictions and rely on post-processing to remove duplicate predictions. Detective is a sparse object detector that generates a single bounding box per object instance. However, training a sparse object detector is challenging, as it requires the model to reason at the instance level and not just at the class and spatial levels. We propose a training mechanism based on the Hungarian Algorithm and a loss that balances the localization and classification tasks. This allows Detective to achieve promising results on the PASCAL VOC object detection dataset. Our experiments demonstrate that sparse object detection is possible and has a great potential for future developments in applications where the order of the objects to be predicted is of interest.

Textual-Content Based Classification of Bundles of Untranscribed of Manuscript Images

José Ramón Prieto Fontcuberta, Enrique Vidal, Vicente Bosch, Carlos Alonso, Carmen Orcero, Lourdes Márquez

Responsive image

Auto-TLDR; Probabilistic Indexing for Text-based Classification of Manuscripts

Slides Poster Similar

Content-based classification of manuscripts is an important task that is generally performed in archives and libraries by experts with a wealth of knowledge on the manuscripts contents. Unfortunately, many manuscript collections are so vast that it is not feasible to rely solely on experts to perform this task. Current approaches for textual-content-based manuscript classification generally require the handwritten images to be first transcribed into text -- but achieving sufficiently accurate transcripts is generally unfeasible for large sets of historical manuscripts. We propose a new approach to automatically perform this classification task which does not rely on any explicit image transcripts. It is based on ``probabilistic indexing'', a relatively novel technology which allows to effectively represent the intrinsic word-level uncertainty generally exhibited by handwritten text images. We assess the performance of this approach on a large collection of complex manuscripts from the Spanish Archivo General de Indias, with promising results.

Region and Relations Based Multi Attention Network for Graph Classification

Manasvi Aggarwal, M. Narasimha Murty

Responsive image

Auto-TLDR; R2POOL: A Graph Pooling Layer for Non-euclidean Structures

Slides Poster Similar

Graphs are non-euclidean structures that can represent many relational data efficiently. Many studies have proposed the convolution and the pooling operators on the non-euclidean domain. The graph convolution operators have shown astounding performance on various tasks such as node representation and classification. For graph classification, different pooling techniques are introduced, but none of them has considered both neighborhood of the node and the long-range dependencies of the node. In this paper, we propose a novel graph pooling layer R2POOL, which balances the structure information around the node as well as the dependencies with far away nodes. Further, we propose a new training strategy to learn coarse to fine representations. We add supervision at only intermediate levels to generate predictions using only intermediate-level features. For this, we propose the concept of an alignment score. Moreover, each layer's prediction is controlled by our proposed branch training strategy. This complete training helps in learning dominant class features at each layer for representing graphs. We call the combined model by R2MAN. Experiments show that R2MAN the potential to improve the performance of graph classification on various datasets.

Equation Attention Relationship Network (EARN) : A Geometric Deep Metric Framework for Learning Similar Math Expression Embedding

Saleem Ahmed, Kenny Davila, Srirangaraj Setlur, Venu Govindaraju

Responsive image

Auto-TLDR; Representational Learning for Similarity Based Retrieval of Mathematical Expressions

Slides Poster Similar

Representational Learning in the form of high dimensional embeddings have been used for multiple pattern recognition applications. There has been a significant interest in building embedding based systems for learning representationsin the mathematical domain. At the same time, retrieval of structured information such as mathematical expressions is an important need for modern IR systems. In this work, our motivation is to introduce a robust framework for learning representations for similarity based retrieval of mathematical expressions. Given a query by example, the embedding can find the closest matching expression as a function of euclidean distance between them. We leverage recent advancements in image-based and graph-based deep learning algorithms to learn our similarity embeddings. We do this first, by using uni-modal encoders in graph space and image space and then, a multi-modal combination of the same. To overcome the lack of training data, we force the networks to learn a deep metric using triplets generated with a heuristic scoring function. We also adopt a custom strategy for mining hard samples to train our neural networks. Our system produces rankings similar to those generated by the original scoring function, but using only a fraction of the time. Our results establish the viability of using such a multi-modal embedding for this task.

Self-Supervised Learning with Graph Neural Networks for Region of Interest Retrieval in Histopathology

Yigit Ozen, Selim Aksoy, Kemal Kosemehmetoglu, Sevgen Onder, Aysegul Uner

Responsive image

Auto-TLDR; Self-supervised Contrastive Learning for Deep Representation Learning of Histopathology Images

Slides Poster Similar

Deep learning has achieved successful performance in representation learning and content-based retrieval of histopathology images. The commonly used setting in deep learning-based approaches is supervised training of deep neural networks for classification, and using the trained model to extract representations that are used for computing and ranking the distances between images. However, there are two remaining major challenges. First, supervised training of deep neural networks requires large amount of manually labeled data which is often limited in the medical field. Transfer learning has been used to overcome this challenge, but its success remained limited. Second, the clinical practice in histopathology necessitates working with regions of interest (ROI) of multiple diagnostic classes with arbitrary shapes and sizes. The typical solution to this problem is to aggregate the representations of fixed-sized patches cropped from these regions to obtain region-level representations. However, naive methods cannot sufficiently exploit the rich contextual information in the complex tissue structures. To tackle these two challenges, we propose a generic method that utilizes graph neural networks (GNN), combined with a self-supervised training method using a contrastive loss. GNN enables representing arbitrarily-shaped ROIs as graphs and encoding contextual information. Self-supervised contrastive learning improves quality of learned representations without requiring labeled data. The experiments using a challenging breast histopathology data set show that the proposed method achieves better performance than the state-of-the-art.

Supporting Skin Lesion Diagnosis with Content-Based Image Retrieval

Stefano Allegretti, Federico Bolelli, Federico Pollastri, Sabrina Longhitano, Giovanni Pellacani, Costantino Grana

Responsive image

Auto-TLDR; Skin Images Retrieval Using Convolutional Neural Networks for Skin Lesion Classification and Segmentation

Slides Poster Similar

Given the relevance of skin cancer, many attempts have been dedicated to the creation of automated devices that could assist both expert and beginner dermatologists towards fast and early diagnosis of skin lesions. In recent years, tasks such as skin lesion classification and segmentation have been extensively addressed with deep learning algorithms, which in some cases reach a diagnostic accuracy comparable to that of expert physicians. However, the general lack of interpretability and reliability severely hinders the ability of those approaches to actually support dermatologists in the diagnosis process. In this paper a novel skin images retrieval system is presented, which exploits features extracted by Convolutional Neural Networks to gather similar images from a publicly available dataset, in order to assist the diagnosis process of both expert and novice practitioners. In the proposed framework, Resnet-50 is initially trained for the classification of dermoscopic images; then, the feature extraction part is isolated, and an embedding network is build on top of it. The embedding learns an alternative representation, which allows to check image similarity by means of a distance measure. Experimental results reveal that the proposed method is able to select meaningful images, which can effectively boost the classification accuracy of human dermatologists.

Generative Latent Implicit Conditional Optimization When Learning from Small Sample

Idan Azuri, Daphna Weinshall

Responsive image

Auto-TLDR; GLICO: Generative Latent Implicit Conditional Optimization for Small Sample Learning

Slides Poster Similar

We revisit the long-standing problem of learning from small sample. The generation of new samples from a small training set of labeled points has attracted increased attention in recent years. In this paper, we propose a novel such method called GLICO (Generative Latent Implicit Conditional Optimization). GLICO learns a mapping from the training examples to a latent space and a generator that generates images from vectors in the latent space. Unlike most recent work, which rely on access to large amounts of unlabeled data, GLICO does not require access to any additional data other than the small set of labeled points. In fact, GLICO learns to synthesize completely new samples for every class using as little as 5 or 10 examples per class, with as few as 10 such classes and no data from unknown classes. GLICO is then used to augment the small training set while training a classifier on the small sample. To this end, our proposed method samples the learned latent space using spherical interpolation (slerp) and generates new examples using the trained generator. Empirical results show that the new sampled set is diverse enough, leading to improvement in image classification in comparison with the state of the art when trained on small samples obtained from CIFAR-10, CIFAR-100, and CUB-200.

PICK: Processing Key Information Extraction from Documents Using Improved Graph Learning-Convolutional Networks

Wenwen Yu, Ning Lu, Xianbiao Qi, Ping Gong, Rong Xiao

Responsive image

Auto-TLDR; PICK: A Graph Learning Framework for Key Information Extraction from Documents

Slides Poster Similar

Computer vision with state-of-the-art deep learning models have achieved huge success in the field of Optical Character Recognition (OCR) including text detection and recognition tasks recently. However, Key Information Extraction (KIE) from documents as the downstream task of OCR, having a large number of use scenarios in real-world, remains a challenge because documents not only have textual features extracting from OCR systems but also have semantic visual features that are not fully exploited and play a critical role in KIE. Too little work has been devoted to efficiently make full use of both textual and visual features of the documents. In this paper, we introduce PICK, a framework that is effective and robust in handling complex documents layout for KIE by combining graph learning with graph convolution operation, yielding a richer semantic representation containing the textual and visual features and global layout without ambiguity. Extensive experiments on real-world datasets have been conducted to show that our method outperforms baselines methods by significant margins.