Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cheng, De, He, Lingfeng, Wang, Nannan, Zhang, Shizhou, Wang, Zhen, Gao, Xinbo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909374783422464
author Cheng, De
He, Lingfeng
Wang, Nannan
Zhang, Shizhou
Wang, Zhen
Gao, Xinbo
author_facet Cheng, De
He, Lingfeng
Wang, Nannan
Zhang, Shizhou
Wang, Zhen
Gao, Xinbo
contents Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to match pedestrian images of the same identity from different modalities without annotations. Existing works mainly focus on alleviating the modality gap by aligning instance-level features of the unlabeled samples. However, the relationships between cross-modality clusters are not well explored. To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters. Specifically, we design a Many-to-many Bilateral Cross-Modality Cluster Matching (MBCCM) algorithm through optimizing the maximum matching problem in a bipartite graph. Then, the matched pairwise clusters utilize shared visible and infrared pseudo-labels during the model training. Under such a supervisory signal, a Modality-Specific and Modality-Agnostic (MSMA) contrastive learning framework is proposed to align features jointly at a cluster-level. Meanwhile, the cross-modality Consistency Constraint (CC) is proposed to explicitly reduce the large modality discrepancy. Extensive experiments on the public SYSU-MM01 and RegDB datasets demonstrate the effectiveness of the proposed method, surpassing state-of-the-art approaches by a large margin of 8.76% mAP on average.
format Preprint
id arxiv_https___arxiv_org_abs_2305_12673
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID
Cheng, De
He, Lingfeng
Wang, Nannan
Zhang, Shizhou
Wang, Zhen
Gao, Xinbo
Computer Vision and Pattern Recognition
Artificial Intelligence
Unsupervised visible-infrared person re-identification (USL-VI-ReID) aims to match pedestrian images of the same identity from different modalities without annotations. Existing works mainly focus on alleviating the modality gap by aligning instance-level features of the unlabeled samples. However, the relationships between cross-modality clusters are not well explored. To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters. Specifically, we design a Many-to-many Bilateral Cross-Modality Cluster Matching (MBCCM) algorithm through optimizing the maximum matching problem in a bipartite graph. Then, the matched pairwise clusters utilize shared visible and infrared pseudo-labels during the model training. Under such a supervisory signal, a Modality-Specific and Modality-Agnostic (MSMA) contrastive learning framework is proposed to align features jointly at a cluster-level. Meanwhile, the cross-modality Consistency Constraint (CC) is proposed to explicitly reduce the large modality discrepancy. Extensive experiments on the public SYSU-MM01 and RegDB datasets demonstrate the effectiveness of the proposed method, surpassing state-of-the-art approaches by a large margin of 8.76% mAP on average.
title Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2305.12673