Semantic Consistency And Integrity Network For Cloth-changing Person Re-identification

Abstract

Cloth-changing Person Re-identification aims to retrieve target pedestrians across different cameras under clothing-changing scenarios. In recent years, many scholars have made significant explorations in this field. However, existing methods often overlook the semantic consistency and integrity of features. To address this issue, we design a Semantic Consistency and Integrity Network (SCI-Net) to learn semantically invariant features and strip clothing bias from identity features while maintaining their semantic integrity. The network consists of three branches: clothing branch, raw image branch, and head feature enhancement branch. Specifically, we first propose a Head Soft Attention Generation Module to produce head soft attention, thereby obtaining enhanced head features. Then, to ensure that raw features can effectively learn invariant semantic information from head-enhanced features, Semantic Consistency Constraint is proposed to facilitate mutual learning between the two branches. Finally, we leverage knowledge transfer to enable clothing branch to perceive clothing bias entangled with raw features and simulate causal intervention to quantify and remove clothing bias. Experiments on the LTCC-ReID and PRCC datasets demonstrate that our model outperforms other state-of-the-art methods.