Dual-Prompt CLIP with Hybrid Visual Encoders for Occluded Person Re-Identification

TL;DR

This paper introduces DPL-ReID, a novel approach for occluded person re-identification that leverages dual prompt learning, real-world occlusion augmentation, and feature fusion to improve robustness and accuracy.

Contribution

It proposes a dual prompt learning strategy combined with occlusion augmentation and feature fusion, advancing state-of-the-art performance in occluded person ReID.

Findings

Achieves state-of-the-art results on benchmark occluded ReID datasets.

Demonstrates robustness against various occlusion scenarios.

Enriches occluded samples with realistic augmentation.

Abstract

Occluded person re-identification focuses on matching partially visible pedestrians across multiple camera views. However, occlusions disrupt body-region cues, thereby complicating cross-view matching. Most person ReID methods built on pretrained vision-language models only focus on enhancing prompt-based feature learning while ignoring the semantic information of occluders. Based on the success of CLIP-ReID, we propose a novel Dual Prompt Learning ReID (DPL-ReID) model for occluded person ReID. It incorporates a Dual Prompt Learning (Dual-PL) strategy, which can utilize textual cues to capture complete pedestrian semantics and keep robustness against occlusion, and a Real-World Occlusion Augmentation (RWOA) method that realistically simulates occlusion scenarios encountered in real word to enrich occluded samples. In addition, we also design a Weighted Gated Feature Fusion (WGFF) method, which in corporates LSNet to capture global information and act as a feature-gating mechanism. This mechanism can effectively guide the CLIP visual encoder toward generating more comprehensive feature representations. Extensive experiments on several benchmark occluded ReID datasets show that our proposed DPL-ReID achieves the state-of-the art performance. The occlusion instance library are available at https://github.com/stone-qiao/DPL-ReID.