Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Weizhen, Deng, Yiheng, Tang, Shixiang, Chen, Qihao, Xie, Qingsong, Wang, Yizhou, Bai, Lei, Zhu, Feng, Zhao, Rui, Ouyang, Wanli, Qi, Donglian, Yan, Yunfeng
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915264168198144
author He, Weizhen
Deng, Yiheng
Tang, Shixiang
Chen, Qihao
Xie, Qingsong
Wang, Yizhou
Bai, Lei
Zhu, Feng
Zhao, Rui
Ouyang, Wanli
Qi, Donglian
Yan, Yunfeng
author_facet He, Weizhen
Deng, Yiheng
Tang, Shixiang
Chen, Qihao
Xie, Qingsong
Wang, Yizhou
Bai, Lei
Zhu, Feng
Zhao, Rui
Ouyang, Wanli
Qi, Donglian
Yan, Yunfeng
contents Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which limits the applications in the real world. This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions. Our instruct-ReID is a more general ReID setting, where existing 6 ReID tasks can be viewed as special cases by designing different instructions. We propose a large-scale OmniReID benchmark and an adaptive triplet loss as a baseline method to facilitate research in this new setting. Experimental results show that the proposed multi-purpose ReID model, trained on our OmniReID benchmark without fine-tuning, can improve +0.5%, +0.6%, +7.7% mAP on Market1501, MSMT17, CUHK03 for traditional ReID, +6.4%, +7.1%, +11.2% mAP on PRCC, VC-Clothes, LTCC for clothes-changing ReID, +11.7% mAP on COCAS+ real2 for clothes template based clothes-changing ReID when using only RGB images, +24.9% mAP on COCAS+ real2 for our newly defined language-instructed ReID, +4.3% on LLCM for visible-infrared ReID, +2.6% on CUHK-PEDES for text-to-image ReID. The datasets, the model, and code will be available at https://github.com/hwz-zju/Instruct-ReID.
format Preprint
id arxiv_https___arxiv_org_abs_2306_07520
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
He, Weizhen
Deng, Yiheng
Tang, Shixiang
Chen, Qihao
Xie, Qingsong
Wang, Yizhou
Bai, Lei
Zhu, Feng
Zhao, Rui
Ouyang, Wanli
Qi, Donglian
Yan, Yunfeng
Computer Vision and Pattern Recognition
Human intelligence can retrieve any person according to both visual and language descriptions. However, the current computer vision community studies specific person re-identification (ReID) tasks in different scenarios separately, which limits the applications in the real world. This paper strives to resolve this problem by proposing a new instruct-ReID task that requires the model to retrieve images according to the given image or language instructions. Our instruct-ReID is a more general ReID setting, where existing 6 ReID tasks can be viewed as special cases by designing different instructions. We propose a large-scale OmniReID benchmark and an adaptive triplet loss as a baseline method to facilitate research in this new setting. Experimental results show that the proposed multi-purpose ReID model, trained on our OmniReID benchmark without fine-tuning, can improve +0.5%, +0.6%, +7.7% mAP on Market1501, MSMT17, CUHK03 for traditional ReID, +6.4%, +7.1%, +11.2% mAP on PRCC, VC-Clothes, LTCC for clothes-changing ReID, +11.7% mAP on COCAS+ real2 for clothes template based clothes-changing ReID when using only RGB images, +24.9% mAP on COCAS+ real2 for our newly defined language-instructed ReID, +4.3% on LLCM for visible-infrared ReID, +2.6% on CUHK-PEDES for text-to-image ReID. The datasets, the model, and code will be available at https://github.com/hwz-zju/Instruct-ReID.
title Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.07520