Scholarlink

<p>Person Re-Identification (Re-ID) involves matching pedestrian images across camera networks with non-overlapping views. This task is challenging due to variations in illumination, viewpoints, background clutter, and occlusions, which often degrade model performance and consistency. Addressing these issues requires features that are robust to such variations. We introduce a deep self-attention module named deeply supervised person (DSP) for Re-ID, designed to learn and fuse spatial and cross-channel relationships throughout the feature extraction process. By decomposing attention into channel and spatial dimensions, our approach enhances the robustness of the learned features. The module employs global feature aggregation and normalization, yielding more discriminative and complementary features. Our model is structured as a fine-grained classification problem, optimized using multi-class cross-entropy loss, and enhanced with losses from deeply supervised intermediate layers, partitioned regions, and final classification. Extensive experiments on the DukeMTMC-ReID and Market-1501 datasets show that our model surpasses the baseline, with improvements of 6.6% and 6.2% in Rank-1 accuracy, respectively. Additionally, our model delivers superior and competitive performance compared to current state-of-the-art methods. (Code and further illustration will be will be available at <a href="https://github.com/bmiftah/DSP_Person_ReID">https://github.com/bmiftah/DSP_Person_ReID</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

Deeply supervised self-attention learning model for person re-identification

  • 期刊论文

  • 发表日期：

    2026年1月16日

查看全文
  • Miftah Bedru Jamal,
  • Yaping Zhao

摘要

Person Re-Identification (Re-ID) involves matching pedestrian images across camera networks with non-overlapping views. This task is challenging due to variations in illumination, viewpoints, background clutter, and occlusions, which often degrade model performance and consistency. Addressing these issues requires features that are robust to such variations. We introduce a deep self-attention module named deeply supervised person (DSP) for Re-ID, designed to learn and fuse spatial and cross-channel relationships throughout the feature extraction process. By decomposing attention into channel and spatial dimensions, our approach enhances the robustness of the learned features. The module employs global feature aggregation and normalization, yielding more discriminative and complementary features. Our model is structured as a fine-grained classification problem, optimized using multi-class cross-entropy loss, and enhanced with losses from deeply supervised intermediate layers, partitioned regions, and final classification. Extensive experiments on the DukeMTMC-ReID and Market-1501 datasets show that our model surpasses the baseline, with improvements of 6.6% and 6.2% in Rank-1 accuracy, respectively. Additionally, our model delivers superior and competitive performance compared to current state-of-the-art methods. (Code and further illustration will be will be available at https://github.com/bmiftah/DSP_Person_ReID)