CASIA OpenIR  > 紫东太初大模型研究中心
PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
Zhu Kuan; Guo Haiyun; Yan Tianyi; Zhu Yousong; Wang Jinqiao; Tang Ming
Conference NameEuropean Conference on Computer Vision 2022
Conference Date2022-7
Conference Place线上

In person re-identification (ReID), very recent researches have validated pre-training the models on unlabelled person images is much better than on ImageNet. However, these researches directly apply the existing self-supervised learning (SSL) methods designed for image classification to ReID without any adaption in the framework. These SSL methods match the outputs of local views (e.g., red T-shirt, blue shorts) to those of the global views at the same time, losing lots of details. In this paper, we propose a ReID-specific pre-training method, Part-Aware Self-Supervised pre-training (PASS), which can generate part-level features to offer fine-grained information and is more suitable for ReID. PASS divides the images into several local areas, and the local views randomly cropped from each area are assigned a specific learnable [PART] token. On the other hand, the [PART]s of all local areas are also appended to the global views. PASS learns to match the outputs of the local views and global views on the same [PART]. That is, the learned [PART] of the local views from a local area is only matched with the corresponding [PART] learned from the global views. As a result, each [PART] can focus on a specific local area of the image and extracts fine-grained information of this area. Experiments show PASS sets the new state-of-the-art performances on Market1501 and MSMT17 on various ReID tasks, e.g., vanilla ViT-S/16 pre-trained by PASS achieves 92.2%/90.2%/88.5% mAP accuracy on Market1501 for supervised/UDA/USL ReID. Our codes are available at

Indexed ByEI
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory视觉信息处理
Paper associated data
Document Type会议论文
Recommended Citation
GB/T 7714
Zhu Kuan,Guo Haiyun,Yan Tianyi,et al. PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
PASS.pdf(894KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu Kuan]'s Articles
[Guo Haiyun]'s Articles
[Yan Tianyi]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu Kuan]'s Articles
[Guo Haiyun]'s Articles
[Yan Tianyi]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu Kuan]'s Articles
[Guo Haiyun]'s Articles
[Yan Tianyi]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PASS.pdf
Format: Adobe PDF
All comments (0)
No comment.

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