Filters








2,598 Hits in 7.0 sec

Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis [article]

Devinder Kumar, Parthipan Siva, Paul Marchwica, Alexander Wong
2020 arXiv   pre-print
In this paper, we address the aforementioned challenges faced in person re-identification for real-world, practical scenarios by introducing a novel, unsupervised domain adaptation approach for person  ...  While recent success has been achieved via supervised learning using deep neural networks, such methods have limited widespread adoption due to the need for large-scale, customized data annotation.  ...  Conclusion In this work, we presented new strategies for unsupervised person re-ID using unlabelled data from a target domain.  ... 
arXiv:2001.04928v1 fatcat:p3kwnyb4bnebfhwhydjq2gvwaq

Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesis

Devinder Kumar, Parthipan Siva, Paul Marchwica, Alexander Wong
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
In this paper, we address the aforementioned challenges faced in person re-identification for real-world, practical scenarios by introducing a novel, unsupervised domain adaptation approach for person  ...  While recent success has been achieved via supervised learning using deep neural networks, such methods have limited widespread adoption due to the need for large-scale, customized data annotation.  ...  Conclusion In this work, we presented new strategies for unsupervised person re-ID using unlabelled data from a target domain.  ... 
doi:10.1109/wacv45572.2020.9093606 dblp:conf/wacv/KumarSMW20 fatcat:qcdsyzsbsfe5fgvz7dc73jxejy

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification [article]

Yang Zou, Xiaodong Yang, Zhiding Yu, B.V.K. Vijaya Kumar, Jan Kautz
2020 arXiv   pre-print
Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps.  ...  Recently, there has been a growing interest in using unsupervised domain adaptation to address this scalability issue.  ...  First, we propose a joint learning framework for unsupervised cross-domain person re-id to disentangle id-related/unrelated factors so that adaptation can be more effectively performed on the id-related  ... 
arXiv:2007.10315v1 fatcat:b63qxatktrbcpnsklapuzmuoey

Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions [article]

Xiangtan Lin and Pengzhen Ren and Chung-Hsing Yeh and Lina Yao and Andy Song and Xiaojun Chang
2021 arXiv   pre-print
Therefore, unsupervised person Re-ID has drawn increasing attention for its potential to address the scalability issue in person Re-ID.  ...  Unsupervised person Re-ID is challenging primarily due to lacking identity labels to supervise person feature learning.  ...  Unsupervised cross-domain person re-identification In Unsupervised cross-domain person Re-Id, a labelled source domain and an unlabeled target domain are used to train a Re-ID model for the target domain  ... 
arXiv:2109.06057v2 fatcat:epfow7w3trevff5iku2uvb4ov4

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey [article]

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
2020 arXiv   pre-print
in autonomous systems, including image style transfer, image superresolution, image deblurring/dehazing/rain removal, semantic segmentation, depth estimation, pedestrian detection and person re-identification  ...  (re-ID).  ...  Person re-identification. A similar while more difficult task than pedestrian detection, person re-identification (re-ID), requires matching pedestrians in disjoint camera views.  ... 
arXiv:2003.12948v3 fatcat:qtmjs74p2vh6thdotbhgebdvoi

Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation [article]

Zhipeng Huang, Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Peng Chu, Quanzeng You, Jiang Wang, Zicheng Liu, Zheng-jun Zha
2022 arXiv   pre-print
Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps.  ...  In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID.  ...  Our contributions can be summarized in three aspects: Related Works Domain Adaptive Person Re-identification Person re-identification (ReID) has been widely investigated and applied in many real-world  ... 
arXiv:2112.06632v2 fatcat:sninsegzbjhkrcw6vmmr22mxaq

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
2020 Patterns  
re-identification.  ...  Finally, we discuss several challenges and future topics for the use of adversarial learning, RL, and meta-learning in autonomous systems.  ...  ACKNOWLEDGMENTS The authors would like to thank the Editor-in-Chief, Scientific Editor, and anonymous referees for their helpful comments and suggestions, which have greatly improved this paper.  ... 
doi:10.1016/j.patter.2020.100050 pmid:33205114 pmcid:PMC7660378 fatcat:vs7wm2yrwjamjbaml36663wvze

Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID [article]

Yixiao Ge, Feng Zhu, Dapeng Chen, Rui Zhao, Hongsheng Li
2020 arXiv   pre-print
Domain adaptive object re-ID aims to transfer the learned knowledge from the labeled source domain to the unlabeled target domain to tackle the open-class re-identification problems.  ...  The hybrid memory dynamically generates source-domain class-level, target-domain cluster-level and un-clustered instance-level supervisory signals for learning feature representations.  ...  (a) Real→real adaptation on person re-ID datasets. Synthetic→real adaptation on person re-ID datasets.  ... 
arXiv:2006.02713v2 fatcat:o3p2qjowcvaudce2twtxpok7fe

Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification [article]

Pengfei Wang, Changxing Ding, Wentao Tan, Mingming Gong, Kui Jia, Dacheng Tao
2021 arXiv   pre-print
Unsupervised Domain Adaptive (UDA) object re-identification (Re-ID) aims at adapting a model trained on a labeled source domain to an unlabeled target domain.  ...  State-of-the-art object Re-ID approaches adopt clustering algorithms to generate pseudo-labels for the unlabeled target domain.  ...  Related Works We review the literature in three parts: 1) unsupervised domain adaptive (UDA) object Re-ID, 2) contrastive learning, and 3) deep learning with noisy labels.  ... 
arXiv:2108.09682v1 fatcat:7kxdkzzf3fevfdcxjmt6eox3nu

Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends [article]

Asmat Zahra, Nazia Perwaiz, Muhammad Shahzad, Muhammad Moazam Fraz
2022 arXiv   pre-print
Person re-identification (Re-ID) is one of the primary components of an automated visual surveillance system.  ...  For the first time a survey of this type have been presented where the person re-Id approaches are reviewed in such solution-oriented perspective.  ...  In [224] domain adaptive person re-id was proposed using unsupervised target domain. Multiple expert brainstorming networks were learned with multiple architectures for optimal re-id.  ... 
arXiv:2202.13121v1 fatcat:luwwbcwspndqpauj4dosmmojee

Deep Visual Domain Adaptation: A Survey [article]

Mei Wang, Weihong Deng
2018 arXiv   pre-print
Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data.  ...  There have been comprehensive surveys for shallow domain adaption, but few timely reviews the emerging deep learning based methods.  ...  Person Re-identification In the community, person re-identification (re-ID) has become increasingly popular.  ... 
arXiv:1802.03601v4 fatcat:d5hwwecipjfjzmh7725lmepzfe

VTBR: Semantic-based Pretraining for Person Re-Identification [article]

Suncheng Xiang, Zirui Zhang, Mengyuan Guan, Hao Chen, Binjie Yan, Ting Liu, Yuzhuo Fu
2021 arXiv   pre-print
However, recent works show a surprising result that ImageNet pretraining has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data.  ...  Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models.  ...  Unsupervised Domain Adaption Our semantic-based pretraining method enjoys the benefits of flexible corner scenarios of domain adaptive Re-ID tasks, where labelled data in target domain is hard to obtain  ... 
arXiv:2110.05074v1 fatcat:nw2qu5ozlvhbzmmlqitloonaxy

StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching

Rui Liu, Chengxi Yang, Wenxiu Sun, Xiaogang Wang, Hongsheng Li
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias.  ...  ., bidirectional multi-scale feature re-projection loss and correlation consistency loss, to help translate all synthetic stereo images into realistic ones as well as maintain epipolar constraints.  ...  segmentation, person re-identification and object detection [15, 41, 32, 3] .  ... 
doi:10.1109/cvpr42600.2020.01277 dblp:conf/cvpr/LiuYSWL20 fatcat:7r6mbp5y3fa2dp42gzyblssmpe

Domain-Adversarial Training of Neural Networks [article]

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky
2016 arXiv   pre-print
We also validate the approach for descriptor learning task in the context of person re-identification application.  ...  We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions.  ...  We also thank the Graphics & Media Lab, Faculty of Computational Mathematics and Cybernetics, Lomonosov Moscow State University for providing the synthetic road signs data set.  ... 
arXiv:1505.07818v4 fatcat:xj7camuj3fagdmfgqqf2mrnmb4

Domain-Adversarial Training of Neural Networks [chapter]

Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky
2017 Advances in Computer Vision and Pattern Recognition  
We also validate the approach for descriptor learning task in the context of person re-identification application.  ...  We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions.  ...  We also thank the Graphics & Media Lab, Faculty of Computational Mathematics and Cybernetics, Lomonosov Moscow State University for providing the synthetic road signs data set.  ... 
doi:10.1007/978-3-319-58347-1_10 fatcat:ysrh2ae6ajfi7jogffieaa7khy
« Previous Showing results 1 — 15 out of 2,598 results