Visible-infrared person re-identification with region-based augmentation and cross modality attention

Abstract Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often introduce inte...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuwei Guo, Wenhao Zhang, Licheng Jiao, Shuang Wang, Shuo Wang, Fang Liu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-01979-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704160534986752
author Yuwei Guo
Wenhao Zhang
Licheng Jiao
Shuang Wang
Shuo Wang
Fang Liu
author_facet Yuwei Guo
Wenhao Zhang
Licheng Jiao
Shuang Wang
Shuo Wang
Fang Liu
author_sort Yuwei Guo
collection DOAJ
description Abstract Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often introduce interfering information and lead to higher computational overhead when generating the corresponding images or features. Additionally, the pedestrian region characteristics in VI-ReID are not effectively utilized, thus resulting in ambiguous or unnatural images. To address these issues, it is critical to leverage pedestrian attentive features and learn modality-complete and -consistent representation. In this paper, a novel Region-based Augmentation and Cross Modality Attention (RACA) model is proposed, focusing on the pedestrian regions to efficiently compensate for missing modality-specific features. Specifically, we propose a region-based data augmentation module PedMix to enhance pedestrian region coherence by mixing the corresponding regions from different modalities, thus generating more natural images. Moreover, a lightweight hybrid compensation module, i.e., a Modality Feature Transfer (MFT) module, is proposed to integrate cross attention and convolution networks to avoid introducing interfering information while preserving minimal computational overhead. Extensive experiments conducted on the benchmark SYSU-MM01 and RegDB datasets demonstrated the effectiveness of our proposed RACA model.
format Article
id doaj-art-116c1fc0c830485a83f0edcf9d8e5fd0
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-116c1fc0c830485a83f0edcf9d8e5fd02025-08-20T03:16:51ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-01979-zVisible-infrared person re-identification with region-based augmentation and cross modality attentionYuwei Guo0Wenhao Zhang1Licheng Jiao2Shuang Wang3Shuo Wang4Fang Liu5Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, School of Artificial Intelligence, International Research Center of Intelligent Perception and Computation, Xidian UniversityKey Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, School of Artificial Intelligence, International Research Center of Intelligent Perception and Computation, Xidian UniversityKey Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, School of Artificial Intelligence, International Research Center of Intelligent Perception and Computation, Xidian UniversityKey Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, School of Artificial Intelligence, International Research Center of Intelligent Perception and Computation, Xidian UniversitySchool of Computer Science, The University of BirminghamKey Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, School of Artificial Intelligence, International Research Center of Intelligent Perception and Computation, Xidian UniversityAbstract Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often introduce interfering information and lead to higher computational overhead when generating the corresponding images or features. Additionally, the pedestrian region characteristics in VI-ReID are not effectively utilized, thus resulting in ambiguous or unnatural images. To address these issues, it is critical to leverage pedestrian attentive features and learn modality-complete and -consistent representation. In this paper, a novel Region-based Augmentation and Cross Modality Attention (RACA) model is proposed, focusing on the pedestrian regions to efficiently compensate for missing modality-specific features. Specifically, we propose a region-based data augmentation module PedMix to enhance pedestrian region coherence by mixing the corresponding regions from different modalities, thus generating more natural images. Moreover, a lightweight hybrid compensation module, i.e., a Modality Feature Transfer (MFT) module, is proposed to integrate cross attention and convolution networks to avoid introducing interfering information while preserving minimal computational overhead. Extensive experiments conducted on the benchmark SYSU-MM01 and RegDB datasets demonstrated the effectiveness of our proposed RACA model.https://doi.org/10.1038/s41598-025-01979-z
spellingShingle Yuwei Guo
Wenhao Zhang
Licheng Jiao
Shuang Wang
Shuo Wang
Fang Liu
Visible-infrared person re-identification with region-based augmentation and cross modality attention
Scientific Reports
title Visible-infrared person re-identification with region-based augmentation and cross modality attention
title_full Visible-infrared person re-identification with region-based augmentation and cross modality attention
title_fullStr Visible-infrared person re-identification with region-based augmentation and cross modality attention
title_full_unstemmed Visible-infrared person re-identification with region-based augmentation and cross modality attention
title_short Visible-infrared person re-identification with region-based augmentation and cross modality attention
title_sort visible infrared person re identification with region based augmentation and cross modality attention
url https://doi.org/10.1038/s41598-025-01979-z
work_keys_str_mv AT yuweiguo visibleinfraredpersonreidentificationwithregionbasedaugmentationandcrossmodalityattention
AT wenhaozhang visibleinfraredpersonreidentificationwithregionbasedaugmentationandcrossmodalityattention
AT lichengjiao visibleinfraredpersonreidentificationwithregionbasedaugmentationandcrossmodalityattention
AT shuangwang visibleinfraredpersonreidentificationwithregionbasedaugmentationandcrossmodalityattention
AT shuowang visibleinfraredpersonreidentificationwithregionbasedaugmentationandcrossmodalityattention
AT fangliu visibleinfraredpersonreidentificationwithregionbasedaugmentationandcrossmodalityattention