SCORE：面向混合衣着终身行人重识别的子分布感知协作知识强化
SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification
- Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
- University of Chinese Academy of Sciences（中国科学院大学）
- Intelligent Science & Technology Academy of CASIC（中国航天科工集团智能科技研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对混合衣着终身行人重识别中衣着相关与无关知识冲突加剧灾难性遗忘的问题，提出子分布感知协作知识强化框架，通过自适应子分布建模和分布性知识强化实现最先进性能。
AI中文摘要：
终身行人重识别（LReID）旨在从非平稳数据流中训练一个统一的行人检索模型。现有的LReID方法主要关注每个人衣着一致的情景。近期，衣着一致与衣着变化数据交替出现的混合衣着LReID（CH-LReID）已成为一个更实际且更具挑战性的场景。由于与衣着相关和与衣着无关的知识之间存在冲突，众所周知的灾难性遗忘问题在此任务中被显著加剧。为解决此问题，我们提出了一种子分布感知的协作知识强化（SCORE）框架，其核心思想是显式建模身份内多样性，以持续巩固不同的衣着一致与衣着变化知识。具体而言，我们开发了一种自适应子分布建模机制，为每个身份分配一组分布性子原型以捕获身份内多样性，从而提高衣着一致与衣着变化知识之间的兼容性。随后，引入了一种分布性知识强化方案，通过协作对齐机制将旧分布性子原型的知识保留在新的子原型中。大量实验表明，我们的SCORE达到了最先进的性能。我们的代码可在以下网址获取：此https URL。
英文摘要：
Lifelong Person Re-Identification (LReID) aims to train a unified person retrieval model from a non-stationary data stream. Existing LReID methods mainly focus on scenarios where the clothing of each person is consistent. Recently, the Cloth-Hybrid LReID (CH-LReID) where cloth-consistent and cloth-changing data alternately occur, has emerged as a more practical and challenging scenario. Due to the conflict between clothing-relevant and clothing-irrelevant knowledge, the well-known catastrophic forgetting problem is significantly exacerbated in this task. To address this issue, we propose a SubDistribution-aware COllaborative Knowledge REinforcing (SCORE) framework, where our key idea is explicitly modeling the intra-identity diversity to continually consolidate distinct cloth-consistent and cloth-changing knowledge. Specifically, an Adaptive SubDistribution Modeling mechanism is developed, where a set of distributional subprototypes is assigned to each identity to capture the intra-identity diversity, improving the compatibility between cloth-consistent and cloth-changing knowledge. Then, a Distributional Knowledge Reinforcement scheme is introduced, where the knowledge of old distributional subprototypes is retained in the new ones by a collaborative aligning mechanism. Extensive experiments show that our SCORE achieves the state-of-the-art performance. Our code is available at https://github.com/zhoujiahuan1991/ECCV2026-SCORE
