Learning Domain Invariant Representations for Generalizable Person Re-Identification
This addresses domain generalization in person re-identification for computer vision applications, representing an incremental improvement.
The paper tackled the problem of generalizable person re-identification by proposing a domain invariant representation learning framework based on causal analysis, which outperformed state-of-the-art methods on large-scale benchmarks.
Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community. In this work, we construct a structural causal model among identity labels, identity-specific factors (clothes/shoes color etc), and domain-specific factors (background, viewpoints etc). According to the causal analysis, we propose a novel Domain Invariant Representation Learning for generalizable person Re-Identification (DIR-ReID) framework. Specifically, we first propose to disentangle the identity-specific and domain-specific feature spaces, based on which we propose an effective algorithmic implementation for backdoor adjustment, essentially serving as a causal intervention towards the SCM. Extensive experiments have been conducted, showing that DIR-ReID outperforms state-of-the-art methods on large-scale domain generalization ReID benchmarks.