arXiv subjects

Eric Granger

Publications and source records attributed to Eric Granger.

At least 127 records · Page 7Linked to original sources

arXiv2021

Transductive Few-Shot Learning: Clustering is All You Need?

We investigate a general formulation for clustering and transductive few-shot learning, which integrates prototype-based objectives, Laplacian regularization and supervision constraints from a few labeled data points. We propose a concave-convex relaxation of the problem, and derive a computationally efficient block-coordinate bound optimizer, with convergence guarantee. At each iteration,our optimizer computes independent (parallel) updates for each point-to-cluster assignment. Therefore, it could be trivially distributed for large-scale clustering and few-shot tasks. Furthermore, we provides a thorough convergence analysis based on point-to-set maps. Were port comprehensive clustering and few-shot learning experiments over various data sets, showing that our method yields competitive performances, in term of accuracy and optimization quality, while scaling up to large problems. Using standard training on the base classes, without resorting to complex meta-learning and episodic-training strategies, our approach outperforms state-of-the-art few-shot methods by significant margins, across various models, settings and data sets. Surprisingly, we found that even standard clustering procedures (e.g., K-means), which correspond to particular, non-regularized cases of our general model, already achieve competitive performances in comparison to the state-of-the-art in few-shot learning. These surprising results point to the limitations of the current few-shot benchmarks, and question the viability of a large body of convoluted few-shot learning techniques in the recent literature.

cs.LG↗

arXiv2021

Laplacian Regularized Few-Shot Learning

We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assigning query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label assignments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to supervision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes independent (parallel) updates for each query sample, while guaranteeing convergence. Following a simple cross-entropy training on the base classes, and without complex meta-learning strategies, we conducted comprehensive experiments over five few-shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our transductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.

cs.LG↗

arXiv2021

Exploiting Prunability for Person Re-Identification

Recent years have witnessed a substantial increase in the deep learning (DL)architectures proposed for visual recognition tasks like person re-identification,where individuals must be recognized over multiple distributed cameras. Althoughthese architectures have greatly improved the state-of-the-art accuracy, thecomputational complexity of the CNNs commonly used for feature extractionremains an issue, hindering their deployment on platforms with limited resources,or in applications with real-time constraints. There is an obvious advantage toaccelerating and compressing DL models without significantly decreasing theiraccuracy. However, the source (pruning) domain differs from operational (target)domains, and the domain shift between image data captured with differentnon-overlapping camera viewpoints leads to lower recognition accuracy. In thispaper, we investigate the prunability of these architectures under different designscenarios. This paper first revisits pruning techniques that are suitable forreducing the computational complexity of deep CNN networks applied to personre-identification. Then, these techniques are analysed according to their pruningcriteria and strategy, and according to different scenarios for exploiting pruningmethods to fine-tuning networks to target domains. Experimental resultsobtained using DL models with ResNet feature extractors, and multiplebenchmarks re-identification datasets, indicate that pruning can considerablyreduce network complexity while maintaining a high level of accuracy. Inscenarios where pruning is performed with large pre-training or fine-tuningdatasets, the number of FLOPS required by ResNet architectures is reduced byhalf, while maintaining a comparable rank-1 accuracy (within 1% of the originalmodel). Pruning while training a larger CNNs can also provide a significantlybetter performance than fine-tuning smaller ones.

cs.CV↗

arXiv2021

Min-max Entropy for Weakly Supervised Pointwise Localization

Pointwise localization allows more precise localization and accurate interpretability, compared to bounding box, in applications where objects are highly unstructured such as in medical domain. In this work, we focus on weakly supervised localization (WSL) where a model is trained to classify an image and localize regions of interest at pixel-level using only global image annotation. Typical convolutional attentions maps are prune to high false positive regions. To alleviate this issue, we propose a new deep learning method for WSL, composed of a localizer and a classifier, where the localizer is constrained to determine relevant and irrelevant regions using conditional entropy (CE) with the aim to reduce false positive regions. Experimental results on a public medical dataset and two natural datasets, using Dice index, show that, compared to state of the art WSL methods, our proposal can provide significant improvements in terms of image-level classification and pixel-level localization (low false positive) with robustness to overfitting. A public reproducible PyTorch implementation is provided in: https://github.com/sbelharbi/wsol-min-max-entropy-interpretability .

cs.CV↗

arXiv2021

Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

Beyond the complexity of CNNs that require training on large annotated datasets, the domain shift between design and operational data has limited the adoption of CNNs in many real-world applications. For instance, in person re-identification, videos are captured over a distributed set of cameras with non-overlapping viewpoints. The shift between the source (e.g. lab setting) and target (e.g. cameras) domains may lead to a significant decline in recognition accuracy. Additionally, state-of-the-art CNNs may not be suitable for such real-time applications given their computational requirements. Although several techniques have recently been proposed to address domain shift problems through unsupervised domain adaptation (UDA), or to accelerate/compress CNNs through knowledge distillation (KD), we seek to simultaneously adapt and compress CNNs to generalize well across multiple target domains. In this paper, we propose a progressive KD approach for unsupervised single-target DA (STDA) and multi-target DA (MTDA) of CNNs. Our method for KD-STDA adapts a CNN to a single target domain by distilling from a larger teacher CNN, trained on both target and source domain data in order to maintain its consistency with a common representation. Our proposed approach is compared against state-of-the-art methods for compression and STDA of CNNs on the Office31 and ImageClef-DA image classification datasets. It is also compared against state-of-the-art methods for MTDA on Digits, Office31, and OfficeHome. In both settings -- KD-STDA and KD-MTDA -- results indicate that our approach can achieve the highest level of accuracy across target domains, while requiring a comparable or lower CNN complexity.

cs.CV↗

arXiv2021

Continuous Emotion Recognition with Spatiotemporal Convolutional Neural Networks

Facial expressions are one of the most powerful ways for depicting specific patterns in human behavior and describing human emotional state. Despite the impressive advances of affective computing over the last decade, automatic video-based systems for facial expression recognition still cannot handle properly variations in facial expression among individuals as well as cross-cultural and demographic aspects. Nevertheless, recognizing facial expressions is a difficult task even for humans. In this paper, we investigate the suitability of state-of-the-art deep learning architectures based on convolutional neural networks (CNNs) for continuous emotion recognition using long video sequences captured in-the-wild. This study focuses on deep learning models that allow encoding spatiotemporal relations in videos considering a complex and multi-dimensional emotion space, where values of valence and arousal must be predicted. We have developed and evaluated convolutional recurrent neural networks combining 2D-CNNs and long short term-memory units, and inflated 3D-CNN models, which are built by inflating the weights of a pre-trained 2D-CNN model during fine-tuning, using application-specific videos. Experimental results on the challenging SEWA-DB dataset have shown that these architectures can effectively be fine-tuned to encode the spatiotemporal information from successive raw pixel images and achieve state-of-the-art results on such a dataset.

cs.CV↗

arXiv2020

Image Synthesis with Adversarial Networks: a Comprehensive Survey and Case Studies

Generative Adversarial Networks (GANs) have been extremely successful in various application domains such as computer vision, medicine, and natural language processing. Moreover, transforming an object or person to a desired shape become a well-studied research in the GANs. GANs are powerful models for learning complex distributions to synthesize semantically meaningful samples. However, there is a lack of comprehensive review in this field, especially lack of a collection of GANs loss-variant, evaluation metrics, remedies for diverse image generation, and stable training. Given the current fast GANs development, in this survey, we provide a comprehensive review of adversarial models for image synthesis. We summarize the synthetic image generation methods, and discuss the categories including image-to-image translation, fusion image generation, label-to-image mapping, and text-to-image translation. We organize the literature based on their base models, developed ideas related to architectures, constraints, loss functions, evaluation metrics, and training datasets. We present milestones of adversarial models, review an extensive selection of previous works in various categories, and present insights on the development route from the model-based to data-driven methods. Further, we highlight a range of potential future research directions. One of the unique features of this review is that all software implementations of these GAN methods and datasets have been collected and made available in one place at https://github.com/pshams55/GAN-Case-Study.

cs.CV↗

arXiv2020

Variational Fair Clustering

We propose a general variational framework of fair clustering, which integrates an original Kullback-Leibler (KL) fairness term with a large class of clustering objectives, including prototype or graph based. Fundamentally different from the existing combinatorial and spectral solutions, our variational multi-term approach enables to control the trade-off levels between the fairness and clustering objectives. We derive a general tight upper bound based on a concave-convex decomposition of our fairness term, its Lipschitz-gradient property and the Pinsker's inequality. Our tight upper bound can be jointly optimized with various clustering objectives, while yielding a scalable solution, with convergence guarantee. Interestingly, at each iteration, it performs an independent update for each assignment variable. Therefore, it can be easily distributed for large-scale datasets. This scalability is important as it enables to explore different trade-off levels between the fairness and clustering objectives. Unlike spectral relaxation, our formulation does not require computing its eigenvalue decomposition. We report comprehensive evaluations and comparisons with state-of-the-art methods over various fair-clustering benchmarks, which show that our variational formulation can yield highly competitive solutions in terms of fairness and clustering objectives.

cs.LG↗

arXiv2020

Convolutional STN for Weakly Supervised Object Localization

Weakly supervised object localization is a challenging task in which the object of interest should be localized while learning its appearance. State-of-the-art methods recycle the architecture of a standard CNN by using the activation maps of the last layer for localizing the object. While this approach is simple and works relatively well, object localization relies on different features than classification, thus, a specialized localization mechanism is required during training to improve performance. In this paper, we propose a convolutional, multi-scale spatial localization network that provides accurate localization for the object of interest. Experimental results on CUB-200-2011 and ImageNet datasets show that our proposed approach provides competitive performance for weakly supervised localization.

cs.CV↗

arXiv2020

Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation

Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift between the distribution of unlabeled data from the target domain w.r.t. labeled data from the source domain. While the single-target UDA scenario is well studied in the literature, Multi-Target Domain Adaptation (MTDA) remains largely unexplored despite its practical importance, e.g., in multi-camera video-surveillance applications. The MTDA problem can be addressed by adapting one specialized model per target domain, although this solution is too costly in many real-world applications. Blending multiple targets for MTDA has been proposed, yet this solution may lead to a reduction in model specificity and accuracy. In this paper, we propose a novel unsupervised MTDA approach to train a CNN that can generalize well across multiple target domains. Our Multi-Teacher MTDA (MT-MTDA) method relies on multi-teacher knowledge distillation (KD) to iteratively distill target domain knowledge from multiple teachers to a common student. The KD process is performed in a progressive manner, where the student is trained by each teacher on how to perform UDA for a specific target, instead of directly learning domain adapted features. Finally, instead of combining the knowledge from each teacher, MT-MTDA alternates between teachers that distill knowledge, thereby preserving the specificity of each target (teacher) when learning to adapt to the student. MT-MTDA is compared against state-of-the-art methods on several challenging UDA benchmarks, and empirical results show that our proposed model can provide a considerably higher level of accuracy across multiple target domains. Our code is available at: https://github.com/LIVIAETS/MT-MTDA

cs.CV↗

arXiv2020

Deep Active Learning for Joint Classification & Segmentation with Weak Annotator

CNN visualization and interpretation methods, like class-activation maps (CAMs), are typically used to highlight the image regions linked to class predictions. These models allow to simultaneously classify images and extract class-dependent saliency maps, without the need for costly pixel-level annotations. However, they typically yield segmentations with high false-positive rates and, therefore, coarse visualisations, more so when processing challenging images, as encountered in histology. To mitigate this issue, we propose an active learning (AL) framework, which progressively integrates pixel-level annotations during training. Given training data with global image-level labels, our deep weakly-supervised learning model jointly performs supervised image-level classification and active learning for segmentation, integrating pixel annotations by an oracle. Unlike standard AL methods that focus on sample selection, we also leverage large numbers of unlabeled images via pseudo-segmentations (i.e., self-learning at the pixel level), and integrate them with the oracle-annotated samples during training. We report extensive experiments over two challenging benchmarks -- high-resolution medical images (histology GlaS data for colon cancer) and natural images (CUB-200-2011 for bird species). Our results indicate that, by simply using random sample selection, the proposed approach can significantly outperform state-of the-art CAMs and AL methods, with an identical oracle-supervision budget. Our code is publicly available.

cs.CV↗

arXiv2020

Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition

Training deep learning models for accurate spatiotemporal recognition of facial expressions in videos requires significant computational resources. For practical reasons, 3D Convolutional Neural Networks (3D CNNs) are usually trained with relatively short clips randomly extracted from videos. However, such uniform sampling is generally sub-optimal because equal importance is assigned to each temporal clip. In this paper, we present a strategy for efficient video-based training of 3D CNNs. It relies on softmax temporal pooling and a weighted sampling mechanism to select the most relevant training clips. The proposed softmax strategy provides several advantages: a reduced computational complexity due to efficient clip sampling, and an improved accuracy since temporal weighting focuses on more relevant clips during both training and inference. Experimental results obtained with the proposed method on several facial expression recognition benchmarks show the benefits of focusing on more informative clips in training videos. In particular, our approach improves performance and computational cost by reducing the impact of inaccurate trimming and coarse annotation of videos, and heterogeneous distribution of visual information across time.

cs.CV↗

arXiv2020

Boundary loss for highly unbalanced segmentation

Widely used loss functions for CNN segmentation, e.g., Dice or cross-entropy, are based on integrals over the segmentation regions. Unfortunately, for highly unbalanced segmentations, such regional summations have values that differ by several orders of magnitude across classes, which affects training performance and stability. We propose a boundary loss, which takes the form of a distance metric on the space of contours, not regions. This can mitigate the difficulties of highly unbalanced problems because it uses integrals over the interface between regions instead of unbalanced integrals over the regions. Furthermore, a boundary loss complements regional information. Inspired by graph-based optimization techniques for computing active-contour flows, we express a non-symmetric $L_2$ distance on the space of contours as a regional integral, which avoids completely local differential computations involving contour points. This yields a boundary loss expressed with the regional softmax probability outputs of the network, which can be easily combined with standard regional losses and implemented with any existing deep network architecture for N-D segmentation. We report comprehensive evaluations and comparisons on different unbalanced problems, showing that our boundary loss can yield significant increases in performances while improving training stability. Our code is publicly available: https://github.com/LIVIAETS/surface-loss .

eess.IV↗

arXiv2020

A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification

Person Re-Identification (ReID) is a challenging problem in many video analytics and surveillance applications, where a person's identity must be associated across a distributed non-overlapping network of cameras. Video-based person ReID has recently gained much interest because it allows capturing discriminant spatio-temporal information from video clips that is unavailable for image-based ReID. Despite recent advances, deep learning (DL) models for video ReID often fail to leverage this information to improve the robustness of feature representations. In this paper, the motion pattern of a person is explored as an additional cue for ReID. In particular, a flow-guided Mutual Attention network is proposed for fusion of image and optical flow sequences using any 2D-CNN backbone, allowing to encode temporal information along with spatial appearance information. Our Mutual Attention network relies on the joint spatial attention between image and optical flow features maps to activate a common set of salient features across them. In addition to flow-guided attention, we introduce a method to aggregate features from longer input streams for better video sequence-level representation. Our extensive experiments on three challenging video ReID datasets indicate that using the proposed Mutual Attention network allows to improve recognition accuracy considerably with respect to conventional gated-attention networks, and state-of-the-art methods for video-based person ReID.

cs.CV↗

arXiv2020

Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

Person re-identification (ReID) remains a challenging task in many real-word video analytics and surveillance applications, even though state-of-the-art accuracy has improved considerably with the advent of deep learning (DL) models trained on large image datasets. Given the shift in distributions that typically occurs between video data captured from the source and target domains, and absence of labeled data from the target domain, it is difficult to adapt a DL model for accurate recognition of target data. We argue that for pair-wise matchers that rely on metric learning, e.g., Siamese networks for person ReID, the unsupervised domain adaptation (UDA) objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations. Moreover, dissimilarity representations are more suitable for designing open-set ReID systems, where identities differ in the source and target domains. In this paper, we propose a novel Dissimilarity-based Maximum Mean Discrepancy (D-MMD) loss for aligning pair-wise distances that can be optimized via gradient descent. From a person ReID perspective, the evaluation of D-MMD loss is straightforward since the tracklet information allows to label a distance vector as being either within-class or between-class. This allows approximating the underlying distribution of target pair-wise distances for D-MMD loss optimization, and accordingly align source and target distance distributions. Empirical results with three challenging benchmark datasets show that the proposed D-MMD loss decreases as source and domain distributions become more similar. Extensive experimental evaluation also indicates that UDA methods that rely on the D-MMD loss can significantly outperform baseline and state-of-the-art UDA methods for person ReID without the common requirement for data augmentation and/or complex networks.

cs.CV↗

arXiv2020

Non-parametric Uni-modality Constraints for Deep Ordinal Classification

We propose a new constrained-optimization formulation for deep ordinal classification, in which uni-modality of the label distribution is enforced implicitly via a set of inequality constraints over all the pairs of adjacent labels. Based on (c-1) constraints for c labels, our model is non-parametric and, therefore, more flexible than the existing deep ordinal classification techniques. Unlike these, it does not restrict the learned representation to a single and specific parametric model (or penalty) imposed on all the labels. Therefore, it enables the training to explore larger spaces of solutions, while removing the need for ad hoc choices and scaling up to large numbers of labels. It can be used in conjunction with any standard classification loss and any deep architecture. To tackle the ensuing challenging optimization problem, we solve a sequence of unconstrained losses based on a powerful extension of the log-barrier method. This handles effectively competing constraints and accommodates standard SGD for deep networks, while avoiding computationally expensive Lagrangian dual steps and outperforming substantially penalty methods. Furthermore, we propose a new performance metric for ordinal classification, as a proxy to measure distribution uni-modality, referred to as the Sides Order Index (SOI). We report comprehensive evaluations and comparisons to state-of-the-art methods on benchmark public datasets for several ordinal classification tasks, showing the merits of our approach in terms of label consistency, classification accuracy and scalability. Importantly, enforcing label consistency with our model does not incur higher classification errors, unlike many existing ordinal classification methods. A public reproducible PyTorch implementation is provided. (https://github.com/sbelharbi/unimodal-prob-deep-oc-free-distribution)

cs.LG↗

arXiv2020

Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation

Currently, the divergence in distributions of design and operational data, and large computational complexity are limiting factors in the adoption of CNNs in real-world applications. For instance, person re-identification systems typically rely on a distributed set of cameras, where each camera has different capture conditions. This can translate to a considerable shift between source (e.g. lab setting) and target (e.g. operational camera) domains. Given the cost of annotating image data captured for fine-tuning in each target domain, unsupervised domain adaptation (UDA) has become a popular approach to adapt CNNs. Moreover, state-of-the-art deep learning models that provide a high level of accuracy often rely on architectures that are too complex for real-time applications. Although several compression and UDA approaches have recently been proposed to overcome these limitations, they do not allow optimizing a CNN to simultaneously address both. In this paper, we propose an unexplored direction -- the joint optimization of CNNs to provide a compressed model that is adapted to perform well for a given target domain. In particular, the proposed approach performs unsupervised knowledge distillation (KD) from a complex teacher model to a compact student model, by leveraging both source and target data. It also improves upon existing UDA techniques by progressively teaching the student about domain-invariant features, instead of directly adapting a compact model on target domain data. Our method is compared against state-of-the-art compression and UDA techniques, using two popular classification datasets for UDA -- Office31 and ImageClef-DA. In both datasets, results indicate that our method can achieve the highest level of accuracy while requiring a comparable or lower time complexity.

cs.LG↗

arXiv2020

Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision

We propose a novel weakly supervised learning segmentation based on several global constraints derived from box annotations. Particularly, we leverage a classical tightness prior to a deep learning setting via imposing a set of constraints on the network outputs. Such a powerful topological prior prevents solutions from excessive shrinking by enforcing any horizontal or vertical line within the bounding box to contain, at least, one pixel of the foreground region. Furthermore, we integrate our deep tightness prior with a global background emptiness constraint, guiding training with information outside the bounding box. We demonstrate experimentally that such a global constraint is much more powerful than standard cross-entropy for the background class. Our optimization problem is challenging as it takes the form of a large set of inequality constraints on the outputs of deep networks. We solve it with sequence of unconstrained losses based on a recent powerful extension of the log-barrier method, which is well-known in the context of interior-point methods. This accommodates standard stochastic gradient descent (SGD) for training deep networks, while avoiding computationally expensive and unstable Lagrangian dual steps and projections. Extensive experiments over two different public data sets and applications (prostate and brain lesions) demonstrate that the synergy between our global tightness and emptiness priors yield very competitive performances, approaching full supervision and outperforming significantly DeepCut. Furthermore, our approach removes the need for computationally expensive proposal generation. Our code is shared anonymously.

cs.CV↗