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
2022-10
会议名称European Conference on Computer Vision 2022
会议日期2022-7
会议地点线上
摘要

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 https://github.com/CASIA-IVA-Lab/PASS-reID.

收录类别EI
七大方向——子方向分类目标检测、跟踪与识别
国重实验室规划方向分类视觉信息处理
是否有论文关联数据集需要存交
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/51930
专题紫东太初大模型研究中心
作者单位1.中国科学院自动化研究所
2.中国科学院大学
推荐引用方式
GB/T 7714
Zhu Kuan,Guo Haiyun,Yan Tianyi,et al. PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification[C],2022.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
PASS.pdf(894KB)会议论文 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
[Zhu Kuan]的文章
[Guo Haiyun]的文章
[Yan Tianyi]的文章
百度学术
百度学术中相似的文章
[Zhu Kuan]的文章
[Guo Haiyun]的文章
[Yan Tianyi]的文章
必应学术
必应学术中相似的文章
[Zhu Kuan]的文章
[Guo Haiyun]的文章
[Yan Tianyi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: PASS.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。