提出新归一化方法，自动分离衣服与身份特征提升换装行人重识别
Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification
- 通过正交空间扩展与通道注意力分离衣物和身份特征
- 在CUHK03和PRW数据集上分别达到86.7%和82.4%的准确率
- 无需额外数据，可无缝集成到ResNet50等主流模型
换装行人重识别（CC-ReID）旨在忽略衣物变化识别同一人。本文实证表明，完全消除或完全保留衣物特征均不利于任务。现有方法依赖衣物标签、轮廓等辅助信息来平衡衣物与身份特征的学习，但实际中难以实现精细平衡。为此，本文提出新型Diverse Norm模块：将个人特征扩展至正交空间，并利用通道注意力分离衣物与身份特征；同时引入样本重加权优化策略，确保两类特征反向优化。该方法不需额外数据，结构简洁有效，可无缝集成于ResNet50，在CUHK03和PRW数据集上分别取得86.7%和82.4%的准确率，显著优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。