Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification
Luo, Chuanchen1,2; Song, Chunfeng1,2; Zhang, Zhaoxiang1,2,3,4
发表期刊IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN0162-8828
2023-02-01
卷号45期号:2页码:1963-1980
摘要

Thanks to the advent of deep neural networks, recent years have witnessed rapid progress in person re-identification (re-ID). Deep-learning-based methods dominate the leadership of large-scale benchmarks, some of which even surpass the human-level performance. Despite their impressive performance under the single-domain setup, current fully-supervised re-ID models degrade significantly when transplanted to an unseen domain. According to the characteristics of the re-ID task, such degradation is mainly attributed to the dramatic variation within the target domain and the severe shift between the source and target domain, which we call dual discrepancy in this paper. To achieve a model that generalizes well to the target domain, it is desirable to take such dual discrepancy into account. In terms of the former issue, a prevailing solution is to enforce consistency between nearest-neighbors in the embedding space. However, we find that the search of neighbors is highly biased in our case due to the discrepancy across cameras. For this reason, we equip the vanilla neighborhood invariance approach with a camera-aware learning scheme. As for the latter issue, we propose a novel cross-domain mixup scheme. It works in conjunction with virtual prototypes which are employed to handle the disjoint label space between the two domains. In this way, we can realize the smooth transfer by introducing the interpolation between the two domains as a transition state. Extensive experiments on four public benchmarks demonstrate the superiority of our method. Without any auxiliary models and offline clustering procedure, it achieves competitive performance against existing state-of-the-art methods. The code is available at https://github.com/LuckyDC/generalizing-reid-improved.

关键词Person re-identification domain adaptation cross-domain mixup camera-aware learning self-paced learning
DOI10.1109/TPAMI.2022.3167053
收录类别SCI
语种英语
资助项目Major Project for New Generation of AI[2018AAA0100400] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62072457] ; National Natural Science Foundation of China[62006231]
项目资助者Major Project for New Generation of AI ; National Natural Science Foundation of China
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000912386000041
出版者IEEE COMPUTER SOC
七大方向——子方向分类生物特征识别
国重实验室规划方向分类多模态协同认知
是否有论文关联数据集需要存交
引用统计
被引频次:3[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/51342
专题多模态人工智能系统全国重点实验室
智能感知与计算
通讯作者Zhang, Zhaoxiang
作者单位1.Chinese Acad Sci, Inst Automat, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit, Beijing 100045, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Beijing 100045, Peoples R China
4.HKISI CAS, Ctr Artificial Intelligence & Robot, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
第一作者单位模式识别国家重点实验室
通讯作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Luo, Chuanchen,Song, Chunfeng,Zhang, Zhaoxiang. Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(2):1963-1980.
APA Luo, Chuanchen,Song, Chunfeng,&Zhang, Zhaoxiang.(2023).Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(2),1963-1980.
MLA Luo, Chuanchen,et al."Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.2(2023):1963-1980.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Learning_to_Adapt_Ac(2539KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Luo, Chuanchen]的文章
[Song, Chunfeng]的文章
[Zhang, Zhaoxiang]的文章
百度学术
百度学术中相似的文章
[Luo, Chuanchen]的文章
[Song, Chunfeng]的文章
[Zhang, Zhaoxiang]的文章
必应学术
必应学术中相似的文章
[Luo, Chuanchen]的文章
[Song, Chunfeng]的文章
[Zhang, Zhaoxiang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Learning_to_Adapt_Across_Dual_Discrepancy_for_Cross-Domain_Person_Re-Identification.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。