Clothes-Invariant Feature Learning by Causal Intervention for Clothes-Changing Person Re-identification

TL;DR

This paper introduces a causal intervention approach for clothes-invariant feature learning in person re-identification, effectively handling clothing changes and achieving state-of-the-art results.

Contribution

It proposes a novel causal intervention method (CCIL) that models clothes-invariant features by addressing confounders, improving upon likelihood-based approaches.

Findings

Achieves state-of-the-art performance on three CC-ReID benchmarks.

Effectively learns clothes-invariant features through causal intervention.

Outperforms existing methods in clothes-changing person re-identification.

Abstract

Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID). It can provide discriminative identity features and eliminate the negative effects caused by the confounder--clothing changes. But we argue that there exists a strong spurious correlation between clothes and human identity, that restricts the common likelihood-based ReID method P(Y|X) to extract clothes-irrelevant features. In this paper, we propose a new Causal Clothes-Invariant Learning (CCIL) method to achieve clothes-invariant feature learning by modeling causal intervention P(Y|do(X)). This new causality-based model is inherently invariant to the confounder in the causal view, which can achieve the clothes-invariant features and avoid the barrier faced by the likelihood-based methods. Extensive experiments on three CC-ReID benchmarks, including PRCC, LTCC, and VC-Clothes, demonstrate the effectiveness of our approach, which achieves a new state of the art.