Exploring Part-Informed Visual-Language Learning for Person Re-Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Yin, Chen, Yehansen, Yin, Baocai, Hu, Jinshui, Yin, Bing, Liu, Cong, Wang, Zengfu
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912284359524352
author Lin, Yin
Chen, Yehansen
Yin, Baocai
Hu, Jinshui
Yin, Bing
Liu, Cong
Wang, Zengfu
author_facet Lin, Yin
Chen, Yehansen
Yin, Baocai
Hu, Jinshui
Yin, Bing
Liu, Cong
Wang, Zengfu
contents Recently, visual-language learning (VLL) has shown great potential in enhancing visual-based person re-identification (ReID). Existing VLL-based ReID methods typically focus on image-text feature alignment at the whole-body level, while neglecting supervision on fine-grained part features, thus lacking constraints for local feature semantic consistency. To this end, we propose Part-Informed Visual-language Learning ($π$-VL) to enhance fine-grained visual features with part-informed language supervisions for ReID tasks. Specifically, $π$-VL introduces a human parsing-guided prompt tuning strategy and a hierarchical visual-language alignment paradigm to ensure within-part feature semantic consistency. The former combines both identity labels and human parsing maps to constitute pixel-level text prompts, and the latter fuses multi-scale visual features with a light-weight auxiliary head to perform fine-grained image-text alignment. As a plug-and-play and inference-free solution, our $π$-VL achieves performance comparable to or better than state-of-the-art methods on four commonly used ReID benchmarks. Notably, it reports 91.0% Rank-1 and 76.9% mAP on the challenging MSMT17 database, without bells and whistles.
format Preprint
id arxiv_https___arxiv_org_abs_2308_02738
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exploring Part-Informed Visual-Language Learning for Person Re-Identification
Lin, Yin
Chen, Yehansen
Yin, Baocai
Hu, Jinshui
Yin, Bing
Liu, Cong
Wang, Zengfu
Computer Vision and Pattern Recognition
Recently, visual-language learning (VLL) has shown great potential in enhancing visual-based person re-identification (ReID). Existing VLL-based ReID methods typically focus on image-text feature alignment at the whole-body level, while neglecting supervision on fine-grained part features, thus lacking constraints for local feature semantic consistency. To this end, we propose Part-Informed Visual-language Learning ($π$-VL) to enhance fine-grained visual features with part-informed language supervisions for ReID tasks. Specifically, $π$-VL introduces a human parsing-guided prompt tuning strategy and a hierarchical visual-language alignment paradigm to ensure within-part feature semantic consistency. The former combines both identity labels and human parsing maps to constitute pixel-level text prompts, and the latter fuses multi-scale visual features with a light-weight auxiliary head to perform fine-grained image-text alignment. As a plug-and-play and inference-free solution, our $π$-VL achieves performance comparable to or better than state-of-the-art methods on four commonly used ReID benchmarks. Notably, it reports 91.0% Rank-1 and 76.9% mAP on the challenging MSMT17 database, without bells and whistles.
title Exploring Part-Informed Visual-Language Learning for Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.02738