DPM++：用于遮挡行人重识别的动态掩码度量学习
DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification
AI总结：
提出DPM++动态掩码度量学习框架，通过自适应掩码选择可靠身份子空间，结合CLIP两阶段监督和显著性引导的补丁转移策略，在遮挡和整体场景下均达到最优性能。
摘要：
尽管行人重识别取得了显著进展，但障碍物造成的遮挡在实际应用中仍是一个未解决的问题。困难在于不完整的遮挡样本与整体身份表示之间的不匹配。严重遮挡会移除判别性身体线索并引入背景杂波和遮挡物的干扰，使得全局度量学习不可靠。现有方法主要依赖额外的预训练模型来估计可见部分以进行对齐，或通过数据增强构建遮挡样本，但仍缺乏一个统一的框架来学习在真实遮挡模式下鲁棒的可见性一致匹配。本文提出了DPM++，一种用于遮挡行人重识别的动态掩码度量学习框架。DPM++学习一种输入自适应的掩码度量，动态地为每个遮挡实例选择可靠的身份子空间，使匹配能够强调可见性一致的证据，同时抑制不可靠的组件。基于分类器-原型空间，DPM++引入了基于CLIP的两阶段监督方案，其中ID级语义先验从文本分支学习并转移到分类器-原型空间中进行动态掩码匹配。为了增强掩码度量，我们引入了一种显著性引导的补丁转移策略，在训练过程中合成可控且逼真的遮挡样本。利用真实场景先验，该策略使模型暴露于真实的部分观察中，并提供比随机擦除更丰富的监督。此外，遮挡感知的样本配对和掩码引导优化提高了框架的稳定性和有效性。在遮挡和整体行人重识别基准上的实验表明，DPM++在整体和遮挡场景中均持续优于先前的最先进方法。
英文摘要：
Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and holistic identity representations. Severe occlusion removes discriminative body cues and introduces interference from background clutter and occluders, making global metric learning unreliable. Existing methods mainly rely on extra pre-trained models to estimate visible parts for alignment or construct occluded samples via data augmentation, but still lack a unified framework that learns robust visibility-consistent matching under realistic occlusion patterns. In this paper, we propose DPM++, a Dynamic Masked Metric Learning framework for occluded person re-identification. DPM++ learns an input-adaptive masked metric that dynamically selects reliable identity subspaces for each occluded instance, enabling matching to emphasize visibility-consistent evidence while suppressing unreliable components. Built upon the classifier-prototype space, DPM++ introduces a CLIP-based two-stage supervision scheme, where ID-level semantic priors are learned from the text branch and transferred into the classifier-prototype space for dynamic masked matching. To strengthen the masked metric, we introduce a saliency-guided patch transfer strategy to synthesize controllable and photo-realistic occluded samples during training. Exploiting real scene priors, this strategy exposes the model to realistic partial observations and provides richer supervision than random erasing. In addition, occlusion-aware sample pairing and mask-guided optimization improve the stability and effectiveness of the framework. Experiments on occluded and holistic person re-identification benchmarks show that DPM++ consistently outperforms previous state-of-the-art methods in both holistic and occlusion scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
