Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification

doi:10.1007/s11263-022-01666-w

	Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification
	Huang, Yukun 1; Fu, Xueyang 1; Li, Liang 2; Zha, Zheng-Jun 1
	2022-09-01
发表期刊	INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN	0920-5691
页码	27
摘要	Person re-identification (Re-ID) in real-world scenarios suffers from various degradations, e.g., low resolution, weak lighting, and bad weather. These degradations hinders identity feature learning and significantly degrades Re-ID performance. To address these issues, in this paper, we propose a degradation invariance learning framework for robust person Re-ID. Concretely, we first design a content-degradation feature disentanglement strategy to capture and isolate task-irrelevant features contained in the degraded image. Then, to avoid the catastrophic forgetting problem, we introduce a memory replay algorithm to further consolidate invariance knowledge learned from the previous pre-training to improve subsequent identity feature learning. In this way, our framework is able to continuously maintain degradation-invariant priors from one or more datasets to improve the robustness of identity features, achieving state-of-the-art Re-ID performance on several challenging real-world benchmarks with a unified model. Furthermore, the proposed framework can be extended to low-level image processing, e.g., low-light image enhancement, demonstrating the potential of our method as a general framework for the various vision tasks. Code and trained models will be available at: https://github.com/hyk1996/Degradati on-Invariant-Re-D-pytorch.
关键词	Person Re-ID Representation learning Vision in bad weather Deep learning Low-light image enhancement
DOI	10.1007/s11263-022-01666-w
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2020AAA0105702] ; National Natural Science Foundation of China (NSFC)[U19B2038] ; National Natural Science Foundation of China (NSFC)[61901433] ; University Synergy Innovation Program of Anhui Province[GXXT-2019-025] ; Fundamental Research Funds for the Central Universities[WK2100000024] ; USTC Research Funds of the Double First-Class Initiative[YD2100002003]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000849289700001
出版者	SPRINGER
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19429
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Fu, Xueyang
作者单位	1.Univ Sci & Technol China, Hefei, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Huang, Yukun,Fu, Xueyang,Li, Liang,et al. Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2022:27.
APA	Huang, Yukun,Fu, Xueyang,Li, Liang,&Zha, Zheng-Jun.(2022).Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification.INTERNATIONAL JOURNAL OF COMPUTER VISION,27.
MLA	Huang, Yukun,et al."Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification".INTERNATIONAL JOURNAL OF COMPUTER VISION (2022):27.