Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification

TL;DR

This paper introduces a novel diffusion model-assisted learning method with correlation-aware conditioning to improve the generalization of person re-identification models across unseen domains, achieving state-of-the-art results.

Contribution

It proposes a new framework integrating pre-trained diffusion models with Re-ID models via correlation-aware prompts to enhance domain generalization.

Findings

Achieves state-of-the-art performance on DG Re-ID benchmarks.

Demonstrates robustness and effectiveness through extensive ablation studies.

Improves generalization by leveraging diffusion model feedback.

Abstract

Domain-generalizable re-identification (DG Re-ID) aims to train a model on one or more source domains and evaluate its performance on unseen target domains, a task that has attracted growing attention due to its practical relevance. While numerous methods have been proposed, most rely on discriminative or contrastive learning frameworks to learn generalizable feature representations. However, these approaches often fail to mitigate shortcut learning, leading to suboptimal performance. In this work, we propose a novel method called diffusion model-assisted representation learning with a correlation-aware conditioning scheme (DCAC) to enhance DG Re-ID. Our method integrates a discriminative and contrastive Re-ID model with a pre-trained diffusion model through a correlation-aware conditioning scheme. By incorporating ID classification probabilities generated from the Re-ID model with a set of learnable ID-wise prompts, the conditioning scheme injects dark knowledge that captures ID correlations to guide the diffusion process. Simultaneously, feedback from the diffusion model is back-propagated through the conditioning scheme to the Re-ID model, effectively improving the generalization capability of Re-ID features. Extensive experiments on both single-source and multi-source DG Re-ID tasks demonstrate that our method achieves state-of-the-art performance. Comprehensive ablation studies further validate the effectiveness of the proposed approach, providing insights into its robustness. Codes will be available at https://github.com/RikoLi/DCAC.