Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search
Benzhi Wang1,2; Yang Yang1; Jinlin Wu1,3; Guo-jun Qi4; Zhen Lei1,2,3
2023-10
Conference NameICCV
Conference Date2023 年 10 月 2 日 – 2023 年 10 月 6 日
Conference Place法国巴黎
Abstract

Weakly supervised person search aims to jointly detect and match persons with only bounding box annotations. Existing approaches typically focus on improving the features by exploring the relations of persons. However, scale variation problem is a more severe obstacle and under-studied that a person often owns images with different scales (resolutions). For one thing, small-scale images contain less information of a person, thus affecting the accuracy of the generated pseudo labels. For another, different similarities between cross-scale images of a person increase the difficulty of matching. In this paper, we address it by proposing a novel one-step framework, named Self-similarity driven Scale-invariant Learning (SSL). Scale invariance can be explored based on the self-similarity prior that it shows the same statistical properties of an image at different scales. To this end, we introduce a Multi-scale Exemplar Branch to guide the network in concentrating on the foreground and learning scaleinvariant features by hard exemplars mining. To enhance the discriminative power of the learned features, we further introduce a dynamic pseudo label prediction that progressively seeks true labels for training. Experimental results on two standard benchmarks, i.e., PRW and CUHKSYSU datasets, demonstrate that the proposed method can solve scale variation problem effectively and perform favorably against state-of-the-art methods

Keyword行人搜索,行人再识别,弱监督学习,度量学习,伪标签预测
Sub direction classification生物特征识别
planning direction of the national heavy laboratory视觉信息处理
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57188
Collection多模态人工智能系统全国重点实验室_生物识别与安全技术
Corresponding AuthorZhen Lei
Affiliation1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences
4.OPPO Research
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Benzhi Wang,Yang Yang,Jinlin Wu,et al. Self-similarity Driven Scale-invariant Learning for Weakly Supervised Person Search[C],2023.
Files in This Item: Download All
File Name/Size DocType Version Access License
Wang_Self-similarity(6488KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Benzhi Wang]'s Articles
[Yang Yang]'s Articles
[Jinlin Wu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Benzhi Wang]'s Articles
[Yang Yang]'s Articles
[Jinlin Wu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Benzhi Wang]'s Articles
[Yang Yang]'s Articles
[Jinlin Wu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Wang_Self-similarity_Driven_Scale-invariant_Learning_for_Weakly_Supervised_Person_Search_ICCV_2023_paper.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.