DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification

TL;DR

DROP introduces a novel approach for occluded person re-identification by decoupling features for re-identification and human parsing, utilizing task-specific features and a part-aware loss to improve accuracy over existing methods.

Contribution

The paper proposes a decoupled feature learning framework for ReID and human parsing, with task-specific feature extraction and a part-aware loss, improving occluded person ReID performance.

Findings

Achieves 76.8% Rank-1 accuracy on Occluded-Duke dataset.

Outperforms mainstream methods in occluded person ReID.

Demonstrates the effectiveness of feature decoupling and task-specific design.

Abstract

The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or relying on semantic information for attention guidance, DROP argues that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features. ReID focuses on instance part-level differences between pedestrian parts, while human parsing centers on semantic spatial context, reflecting the internal structure of the human body. To address this, DROP decouples features for ReID and human parsing, proposing detail-preserving upsampling to combine varying resolution feature maps. Parsing-specific features for human parsing are decoupled, and human position information is exclusively added to the human parsing branch. In the ReID branch, a part-aware compactness loss is introduced to enhance instance-level part differences. Experimental results highlight the efficacy of DROP, especially achieving a Rank-1 accuracy of 76.8% on Occluded-Duke, surpassing two mainstream methods. The codebase is accessible at https://github.com/shuguang-52/DROP.