学习平衡：用于换衣行人重识别的多样化归一化
Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification
AI总结：
本文提出 Diverse Norm 模块，通过正交空间扩展和通道注意力分离服装与身份特征，并采用样本重加权策略优化，无需额外数据即可显著提升换衣行人重识别性能。
摘要：
换衣行人重识别（CC-ReID）涉及在图像中识别个体而不受服装状态影响。本文通过经验和实验证明，完全消除或完全保留服装特征对该任务有害。现有工作无论是依赖服装标签、轮廓还是其他辅助数据，根本上都旨在平衡服装和身份特征的学习。然而，我们在实践中发现实现这种平衡既具挑战性又需细致考量。本研究引入了名为 Diverse Norm 的新模块，将个人特征扩展至正交空间，并利用通道注意力分离服装和身份特征。同时引入样本重加权优化策略，以确保相反的优化方向。Diverse Norm 提供了一种简单有效且无需额外数据的方法。此外，Diverse Norm 可无缝集成至 ResNet50，并显著优于现有最先进方法。
英文摘要：
Cloth-Changing Person Re-Identification (CC-ReID) involves recognizing individuals in images regardless of clothing status. In this paper, we empirically and experimentally demonstrate that completely eliminating or fully retaining clothing features is detrimental to the task. Existing work, either relying on clothing labels, silhouettes, or other auxiliary data, fundamentally aim to balance the learning of clothing and identity features. However, we practically find that achieving this balance is challenging and nuanced. In this study, we introduce a novel module called Diverse Norm, which expands personal features into orthogonal spaces and employs channel attention to separate clothing and identity features. A sample re-weighting optimization strategy is also introduced to guarantee the opposite optimization direction. Diverse Norm presents a simple yet effective approach that does not require additional data. Furthermore, Diverse Norm can be seamlessly integrated ResNet50 and significantly outperforms the state-of-the-art methods.
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。
