原型至关重要：面向无监督可见光-红外行人重识别的模态统一原型自蒸馏
Prototype Matters: Modality-unified Prototype Self-distillation for Unsupervised Visible-infrared Person Re-identification
- Nanjing Normal University（南京师范大学）
- Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出模态统一原型自蒸馏框架，通过联合优化模态内外相似性并利用自原型蒸馏，解决无监督可见光-红外行人重识别的跨模态关联问题。
AI中文摘要：
估计可靠的跨模态关联对于无监督可见光-红外行人重识别至关重要。虽然最优传输已被证明是跨模态关联的一种实用解决方案，但它存在硬标签分配的僵化问题，且未考虑聚类噪声的影响。此外，仅强制执行跨模态对比也是次优的，因为它无法联合优化模态内和模态间的相似性关系。在本文中，我们提出了一种通过充分利用原型进行跨模态学习的新框架：首先，我们证明，与跨模态原型对比不同，模态统一原型对比通过联合并同时优化模态内和模态间的相似性关系，能够促进更好的模态不变性。将自原型作为稳定的教师，我们进一步通过原型引导的自蒸馏来细化实例-原型的在线关系。这两个组件在统一框架中优化，形成了一个简单而有效的模型。在标准的VI-ReID基准上，我们进行了广泛的比较和分析，验证了我们所提出方法的有效性。代码可在以下网址获取：此https URL。
英文摘要：
Estimating reliable cross-modality association is crucial to unsupervised visible-infrared person re-ID. While optimal transport is shown to be a practical solution for cross-modality association, it suffers from the rigidness of hard label assignment without considering the impact of cluster noise. Moreover, enforcing only cross-modality contrast is also suboptimal, as it fails to jointly optimize the similarity relation within and across modality. In this paper, we propose a novel framework for cross-modality learning by well exploitation of prototypes: First, instead of contrasting with cross-modality prototypes, we show that modality-unified prototypical contrast facilitates better modality invariance by jointly and simultaneously optimizing similarity relation within and across-modality. Taking self-prototype as a steady teacher, we further refine the instance-prototype online relation through prototype-guided self-distillation. The two components are optimized in a unified framework, leading to a simple yet effective model. On standard VI-ReID benchmarks, we perform extensive comparison and analysis, validating the effectiveness of our proposed method. Code is available at: https://github.com/Terminator8758/PoSeD.
