检索结果-内蒙古大学图书馆

Vulnerability of Person Re-Identification Models to Metric Adversarial Attacks

学校读者我要写书评

暂无评论

Vulnerability of Person Re-Identification Models to Metric A...

IEEE Computer Society Conference on Computer vision and Pattern Recognition Workshops (CVPRW)

作者： Quentin Bouniot Romaric Audigier Angélique Loesch CEA LIST Vision and Learning Lab for Scene Analysis Gif-sur-Yvette France

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

Person re-identification (re-ID) is a key problem in smart supervision of camera networks. Over the past years, models using deep learning have become state of the art. However, it has been shown that deep neural networks are flawed with adversarial examples, i.e. human-imperceptible perturbations. Extensively studied for the task of image closed- set classification, this problem can also appear in the case of open-set retrieval tasks. Indeed, recent work has shown that we can also generate adversarial examples for metric learning systems such as re-ID ones. These models remain vulnerable: when faced with adversarial examples, they fail to correctly recognize a person, which represents a security breach. These attacks are all the more dangerous as they are impossible to detect for a human operator. Attacking a metric consists in altering the distances between the feature of an attacked image and those of reference images, i.e. guides. In this article, we investigate different possible attacks depending on the number and type of guides available. From this metric attack family, two particularly effective attacks stand out. The first one, called Self Metric Attack, is a strong attack that does not need any image apart from the attacked image. The second one, called FurthestNegative Attack, makes full use of a set of images. Attacks are evaluated on commonly used datasets: Market1501 and DukeMTMC. Finally, we propose an efficient extension of adversarial training protocol adapted to metric learning as a defense that increases the robustness of re-ID models. 1

关键词： Measurement Training Task analysis Protocols Testing Robustness Perturbation methods

PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

学校读者我要写书评

暂无评论

PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Esti...

Conference on Computer vision and Pattern Recognition (CVPR)

作者： Abdallah Benzine Florian Chabot Bertrand Luvison Quoc Cuong Pham Catherine Achard CEA LIST Vision and Learning Lab for Scene Analysis Sorbonne University CNRS Institute for Intelligent Systems and Robotics

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Recently, several deep learning models have been proposed for 3D human pose estimation. Nevertheless, most of these approaches only focus on the single-person case or estimate 3D pose of a few people at high resolution. Furthermore, many applications such as autonomous driving or crowd analysis require pose estimation of a large number of people possibly at low-resolution. In this work, we present PandaNet (Pose estimAtioN and Dectection Anchor-based Network), a new single-shot, anchor-based and multi-person 3D pose estimation approach. The proposed model performs bounding box detection and, for each detected person, 2D and 3D pose regression into a single forward pass. It does not need any post-processing to regroup joints since the network predicts a full 3D pose for each bounding box and allows the pose estimation of a possibly large number of people at low resolution. To manage people overlapping, we introduce a Pose-Aware Anchor Selection strategy. Moreover, as imbalance exists between different people sizes in the image, and joints coordinates have different uncertainties depending on these sizes, we propose a method to automatically optimize weights associated to different people scales and joints for efficient training. PandaNet surpasses previous single-shot methods on several challenging datasets: a multi-person urban virtual but very realistic dataset (JTA Dataset), and two real world 3D multi-person datasets (CMU Panoptic and MuPoTS-3D).

关键词： Three-dimensional displays Two dimensional displays Pose estimation Heating systems Image resolution Solid modeling Skeleton

PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Benzine, Abdallah Chabot, Florian Luvison, Bertrand Pham, Quoc Cuong Achard, Catherine CEA LIST Vision and Learning Lab for Scene Analysis Sorbonne University CNRS Institute for Intelligent Systems and Robotics France

关键词： Deep learning

Classifying All Interacting Pairs in a Single Shot

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chafik, Sanaa Orcesi, Astrid Audigier, Romaric Luvison, Bertrand CEA LIST Vision and Learning Lab for Scene Analysis PC 184 Gif-sur-YvetteF-91191 France Vision Lab ThereSIS Thales SIX GTS Campus Polytechnique Palaiseau France

In this paper, we introduce a novel human interaction detection approach, based on CALIPSO (Classifying ALl Interacting Pairs in a Single shOt), a classifier of human-object interactions. This new single-shot interaction classifier estimates interactions simultaneously for all human-object pairs, regardless of their number and class. State-ofthe-art approaches adopt a multi-shot strategy based on a pairwise estimate of interactions for a set of human-object candidate pairs, which leads to a complexity depending, at least, on the number of interactions or, at most, on the number of candidate pairs. In contrast, the proposed method estimates the interactions on the whole image. Indeed, it simultaneously estimates all interactions between all human subjects and object targets by performing a single forward pass throughout the image. Consequently, it leads to a constant complexity and computation time independent of the number of subjects, objects or interactions in the image. In detail, interaction classification is achieved on a dense grid of anchors thanks to a joint multi-task network that learns three complementary tasks simultaneously: (i) prediction of the types of interaction, (ii) estimation of the presence of a target and (iii) learning of an embedding which maps interacting subject and target to a same representation, by using a metric learning strategy. In addition, we introduce an object-centric passive-voice verb estimation which significantly improves results. Evaluations on the two well-known Human-Object Interaction image datasets, V-COCO and HICO-DET, demonstrate the competitiveness of the proposed method (2nd place) compared to the state-ofthe-art while having constant computation time regardless of the number of objects and interactions in the image. Copyright © 2020, The Authors. All rights reserved.

关键词： Complex networks

Deep, robust and single shot 3D multi-person human pose estimation in complex images

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Benzine, Abdallah Luvison, Bertrand Pham, Quoc Cuong Achard, Catherine CEA LIST Vision and Learning Lab for Scene Analysis PC 184 Gif-sur-YvetteF-91191 France Sorbonne University CNRS Institute for Intelligent Systems and Robotics ISIR ParisF-75005 France

In this paper, we propose a new single shot method for multi-person 3D human pose estimation in complex images. The model jointly learns to locate the human joints in the image, to estimate their 3D coordinates and to group these predictions into full human skeletons. The proposed method deals with a variable number of people and does not need bounding boxes to estimate the 3D poses. It leverages and extends the Stacked Hourglass Network and its multi-scale feature learning to manage multi-person situations. Thus, we exploit a robust 3D human pose formulation to fully describe several 3D human poses even in case of strong occlusions or crops. Then, joint grouping and human pose estimation for an arbitrary number of people are performed using the associative embedding method. Our approach significantly outperforms the state of the art on the challenging CMU Panoptic. Furthermore, it leads to good results on the complex and synthetic images from the newly proposed JTA Dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

Unsupervised Domain Adaptation for Person Re-Identification through source-guided pseudo-labeling

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Dubourvieux, Fabian Audigier, Romaric Loesch, Angelique Ainouz, Samia Canu, Stephane CEA LIST Vision and Learning Lab for Scene Analysis PC 184 Gif-sur-YvetteF-91191 France Normandie Univ INSA Rouen LITIS Av. de l’UniversitÃl’ le Madrillet Saint Etienne du Rouvray76801 France

Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data). Unsupervised Domain Adaptation (UDA) is an interesting research direction for this challenge as it avoids a costly annotation of the target data. Pseudo-labeling methods achieve the best results in UDA-based re-ID. They incrementally learn with identity pseudo-labels which are initialized by clustering features in the source re-ID encoder space. Surprisingly, labeled source data are discarded after this initialization step. However, we believe that pseudo-labeling could further leverage the labeled source data in order to improve the post-initialization training steps. In order to improve robustness against erroneous pseudo-labels, we advocate the exploitation of both labeled source data and pseudo-labeled target data during all training iterations. To support our guideline, we introduce a framework which relies on a two-branch architecture optimizing classification and triplet loss based metric learning in source and target domains, respectively, in order to allow adaptability to the target domain while ensuring robustness to noisy pseudo-labels. Indeed, shared low and mid-level parameters benefit from the source classification and triplet loss signal while high-level parameters of the target branch learn domain-specific features. Our method is simple enough to be easily combined with existing pseudo-labeling UDA approaches. We show experimentally that it is efficient and improves performance when the base method has no mechanism to deal with pseudo-label noise. And it maintains performance when combined with base method that already manages pseudo-label noise. Our approach reaches state-of-the-art performance when evaluated on commonly used datasets, Market-1501 and DukeMTMC

关键词： Machine learning