Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification

TL;DR

This paper introduces a novel multi-component GAN with semantic consistency and identity mapping for robust person re-identification across diverse conditions, achieving superior results on multiple challenging datasets.

Contribution

The paper presents a new GAN architecture with semantic and identity constraints, along with a quartet network and loss for improved person Re-ID performance.

Findings

Outperforms state-of-the-art on six datasets

Effective style adaptation across domains

Maintains identity consistency in generated images

Abstract

In a real world environment, person re-identification (Re-ID) is a challenging task due to variations in lighting conditions, viewing angles, pose and occlusions. Despite recent performance gains, current person Re-ID algorithms still suffer heavily when encountering these variations. To address this problem, we propose a semantic consistency and identity mapping multi-component generative adversarial network (SC-IMGAN) which provides style adaptation from one to many domains. To ensure that transformed images are as realistic as possible, we propose novel identity mapping and semantic consistency losses to maintain identity across the diverse domains. For the Re-ID task, we propose a joint verification-identification quartet network which is trained with generated and real images, followed by an effective quartet loss for verification. Our proposed method outperforms state-of-the-art techniques on six challenging person Re-ID datasets: CUHK01, CUHK03, VIPeR, PRID2011, iLIDS and Market-1501.