Scholarlink

<p>Visible-Infrared person re-identification (VI-ReID) faces significant challenges due to discrepancies between visible and infrared images. Traditional two-stream networks often struggle to preserve semantic guidance from data augmentation as network depth increases. To address this, we propose the Multi-Scale Joint Learning Network (MSJLNet), which employs a novel four-stream architecture to segregate data-augmented branches from original branches, focusing on extracting robust and color-agnostic modal features. An Information Purification Module (IPM) with a channel attention mechanism is designed to dynamically filter noise and suppress redundant color information in the augmented branches. Furthermore, a Joint Semantic Learning Module (JSLM) effectively fuses global detail features with color-agnostic features, improving the model’s discriminative ability. Extensive experiments on the SYSU-MM01 and RegDB datasets demonstrate MSJLNet’s superior performance, achieving 79.94<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation> Rank-1 accuracy and 74.96<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation> mAP on SYSU-MM01, and 93.14<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation> Rank-1 accuracy and 87.22<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation> mAP on RegDB. The proposed approach offers new insights for enhancing cross-modality feature learning. Code is available at <a href="https://github.com/1849714926/MSJLNet">https://github.com/1849714926/MSJLNet</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multi-scale feature fusion for cross-modality person re-identification: the MSJLNet approach

  • 期刊论文

  • 发表日期：

    2026年1月28日

查看全文
  • Zhixin Tie,
  • Haobiao Fan,
  • Lingbing Tao,
  • Yanbing Chen,
  • Hao Sheng,
  • Wei Ke

摘要

Visible-Infrared person re-identification (VI-ReID) faces significant challenges due to discrepancies between visible and infrared images. Traditional two-stream networks often struggle to preserve semantic guidance from data augmentation as network depth increases. To address this, we propose the Multi-Scale Joint Learning Network (MSJLNet), which employs a novel four-stream architecture to segregate data-augmented branches from original branches, focusing on extracting robust and color-agnostic modal features. An Information Purification Module (IPM) with a channel attention mechanism is designed to dynamically filter noise and suppress redundant color information in the augmented branches. Furthermore, a Joint Semantic Learning Module (JSLM) effectively fuses global detail features with color-agnostic features, improving the model’s discriminative ability. Extensive experiments on the SYSU-MM01 and RegDB datasets demonstrate MSJLNet’s superior performance, achieving 79.94 \(\%\) % Rank-1 accuracy and 74.96 \(\%\) % mAP on SYSU-MM01, and 93.14 \(\%\) % Rank-1 accuracy and 87.22 \(\%\) % mAP on RegDB. The proposed approach offers new insights for enhancing cross-modality feature learning. Code is available at https://github.com/1849714926/MSJLNet.