Adaptive Exploration for Unsupervised Person Re-identification

Author:

Ding Yuhang1,Fan Hehe2,Xu Mingliang3,Yang Yi2

Affiliation:

1. SUSTech-UTS Joint Centre of CIS, Southern University of Science and Technology, China

2. Centre for Artificial Intelligence, University of Technology Sydney, Ultimo, Sydney, NSW, Australia

3. School of Information Engineering, Zhengzhou University, Zhengzhou, Henan, China

Abstract

Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this article, we propose an Adaptive Exploration (AE) method to address the domain-shift problem for re-ID in an unsupervised manner. Specifically, in the target domain, the re-ID model is inducted to (1) maximize distances between all person images and (2) minimize distances between similar person images. In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move far away from each other. In the second case, according to a similarity threshold, our method adaptively selects neighborhoods for each person image in the feature space. By treating these similar person images as the same class, the non-parametric classifier forces them to stay closer. However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods. As a result, a minority of images may select a large number of neighborhoods while a majority of images has only a few neighborhoods. To address this issue, we additionally integrate a balance strategy into the adaptive selection. We evaluate our methods with two protocols. The first one is called “target-only re-ID”, in which only the unlabeled target data is used for training. The second one is called “domain adaptive re-ID”, in which both the source data and the target data are used during training. Experimental results on large-scale re-ID datasets demonstrate the effectiveness of our method. Our code has been released at https://github.com/dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture

Cited by 118 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-09-06

2. SAM-driven MAE pre-training and background-aware meta-learning for unsupervised vehicle re-identification;Computational Visual Media;2024-08-15

3. Bridging the Source-to-Target Gap for Cross-Domain Person Re-identification with Intermediate Domains;International Journal of Computer Vision;2024-07-31

4. High Fidelity Makeup via 2D and 3D Identity Preservation Net;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-06-13

5. Style Variable and Irrelevant Learning for Generalizable Person Re-identification;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-06-06

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3