Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification

TL;DR

This paper introduces Color Prompting (CoP), a data-free continual learning method for person re-identification that uses color style transfer to prevent forgetting and adapt quickly to new domains, outperforming replay methods.

Contribution

The novel CoP method employs a lightweight prompter network for color style transfer, achieving effective anti-forgetting and fast adaptation without data rehearsal.

Findings

CoP outperforms replay methods with 6.7% and 8.1% improvements in rank-1 accuracy on seen and unseen domains.

It effectively recovers past color styles, enhancing anti-forgetting capabilities.

CoP demonstrates strong generalization with minimal unlabeled data.

Abstract

Unsupervised domain adaptive person re-identification (Re-ID) methods alleviate the burden of data annotation through generating pseudo supervision messages. However, real-world Re-ID systems, with continuously accumulating data streams, simultaneously demand more robust adaptation and anti-forgetting capabilities. Methods based on image rehearsal addresses the forgetting issue with limited extra storage but carry the risk of privacy leakage. In this work, we propose a Color Prompting (CoP) method for data-free continual unsupervised domain adaptive person Re-ID. Specifically, we employ a light-weighted prompter network to fit the color distribution of the current task together with Re-ID training. Then for the incoming new tasks, the learned color distribution serves as color style transfer guidance to transfer the images into past styles. CoP achieves accurate color style recovery for past tasks with adequate data diversity, leading to superior anti-forgetting effects compared with image rehearsal methods. Moreover, CoP demonstrates strong generalization performance for fast adaptation into new domains, given only a small amount of unlabeled images. Extensive experiments demonstrate that after the continual training pipeline the proposed CoP achieves 6.7% and 8.1% average rank-1 improvements over the replay method on seen and unseen domains, respectively. The source code for this work is publicly available in https://github.com/vimar-gu/ColorPromptReID.