Person re-identification improves with clothing change awareness
SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification
Computer Vision and Pattern Recognition
Summary
Person re-identification means recognizing the same person across different images or video, even when they change clothes. This is a hard problem because the model can forget old information when learning new data, especially when clothing changes. The authors propose a method called SCORE that models different clothing styles for the same person separately and keeps old knowledge from being lost. This method helps the system better identify people despite these clothing changes and improves performance.
What this means in practice
- •For security system developers: Develop person tracking systems that maintain accuracy despite changes in clothing over time by using clothing-aware lifelong learning models.
- •For retail analytics teams: Improve customer re-identification in stores even when shoppers change outfits, enhancing personalization and analytics without loss of past data.
Authors
Kunlun Xu, Liangyu Ma, Jiangmeng Li, Xin Tong, Xiaode Liu, Yufei Guo, Jiahuan Zhou
Abstract
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