COPE：面向遮挡行人重识别的一致遮挡与提示词增强网络
COPE: Consistent Occlusion and Prompt Enhancement Network for Occluded Person Re-identification
针对遮挡行人重识别，CICO 在不同身份上施加相同遮挡并拉近同一遮挡区域的特征，PBF 用视觉-语言对齐生成前景热图做随机背景填充，PSS 用提示词引导的可靠性分数修正检索相似度——这套「一致遮挡 + 提示词可靠性打分」思路可直接迁移到其他存在遮挡或背景干扰的检索/匹配任务。
原文依据 a lightweight Prompt Similarity Scoring (PSS) module refines retrieval similarity by utilizing prompt-guided reliability scores
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论遮挡给行人重识别（Re-ID）带来两个关键挑战：特征干扰与信息丢失。已有工作尝试用遮挡感知的数据增强和特征重建来缓解这些问题，但前者往往无法处理由相似遮挡模式与背景干扰引起的错误匹配，后者则通常引入显著的计算开销。为克服这些局限，本文提出一致遮挡与提示词增强（COPE）网络。COPE 包含一个跨身份一致遮挡（CICO）模块，它对不同身份施加相同的遮挡，并促使不同身份在同一遮挡区域上的特征保持相似，从而减少遮挡特征干扰。提示词背景填充（PBF）模块利用视觉-语言对齐生成前景热图并执行随机背景填充，增强特征在不同背景下的鲁棒性。此外，一个轻量的提示词相似度打分（PSS）模块利用提示词引导的可靠性分数来修正检索相似度。在遮挡与整体行人重识别基准上的大量实验表明，COPE 持续优于现有方法。值得注意的是，在具有挑战性的 Occluded-Duke 数据集上，它取得了 82.4% 的 Rank-1 准确率与 76.4% 的平均精度均值。代码已发布于 https://github.com/Cecoming/COPE。
英文原文摘要 1450 字符
Occlusion presents two critical challenges for person re-identification (Re-ID): feature interference and information loss. While existing efforts have explored occlusion-aware data augmentation and feature reconstruction to mitigate these issues, the former often fails to address erroneous matches caused by similar occlusion patterns and background distractions, whereas the latter typically introduces significant computational overhead. To overcome these limitations, we propose a Consistent Occlusion and Prompt Enhancement (COPE) network. COPE incorporates a Cross-Identity Consistent Occlusion (CICO) module that applies identical occlusions across different identities and encourages feature similarity in the same occluded regions across different identities to reduce occlusion feature interference. A Prompt Background Filling (PBF) module leverages vision-language alignment to generate foreground heatmaps and performs random background filling, enhancing feature robustness under varying backgrounds. Additionally, a lightweight Prompt Similarity Scoring (PSS) module refines retrieval similarity by utilizing prompt-guided reliability scores. Extensive experiments on both occluded and holistic Re-ID benchmarks demonstrate that COPE consistently outperforms existing methods. Notably, it achieves 82.4% Rank-1 accuracy and 76.4% mAP on the challenging Occluded-Duke dataset. The code is available at https://github.com/Cecoming/COPE.