See What You Seek: Semantic Contextual Integration for Cloth-Changing Person Re-Identification

TL;DR

This paper introduces a novel semantic contextual integration framework using CLIP to improve cloth-changing person re-identification by disentangling clothing from ID features and guiding visual representations with text-based semantic cues.

Contribution

The paper proposes a new prompt learning framework with modules for semantic separation and guidance, enhancing ID feature extraction in cloth-changing scenarios.

Findings

Outperforms state-of-the-art on three CC-ReID datasets

Effectively disentangles clothing from identity features

Enhances discriminative power of re-identification models

Abstract

Cloth-changing person re-identification (CC-ReID) aims to match individuals across surveillance cameras despite variations in clothing. Existing methods typically mitigate the impact of clothing changes or enhance identity (ID)-relevant features, but they often struggle to capture complex semantic information. In this paper, we propose a novel prompt learning framework Semantic Contextual Integration (SCI), which leverages the visual-textual representation capabilities of CLIP to reduce clothing-induced discrepancies and strengthen ID cues. Specifically, we introduce the Semantic Separation Enhancement (SSE) module, which employs dual learnable text tokens to disentangle clothing-related semantics from confounding factors, thereby isolating ID-relevant features. Furthermore, we develop a Semantic-Guided Interaction Module (SIM) that uses orthogonalized text features to guide visual representations, sharpening the focus of the model on distinctive ID characteristics. This semantic integration improves the discriminative power of the model and enriches the visual context with high-dimensional insights. Extensive experiments on three CC-ReID datasets demonstrate that our method outperforms state-of-the-art techniques. The code will be released at https://github.com/hxy-499/CCREID-SCI.