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

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.

arXiv commentAccepted in WACV 2020

References in corpus (12)

• A Discriminatively Learned CNN Embedding for Person Re-identification
• PersonNet: Person Re-identification with Deep Convolutional Neural Networks
• Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
• Unsupervised Person Re-identification by Deep Asymmetric Metric Embedding
• Beyond triplet loss: a deep quadruplet network for person re-identification
• Re-ranking Person Re-identification with k-reciprocal Encoding
• Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
• Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
• Multi-Level Factorisation Net for Person Re-Identification
• Embedding Deep Metric for Person Re-identication A Study Against Large Variations
• Scalable Person Re-identification on Supervised Smoothed Manifold
• A Deep Four-Stream Siamese Convolutional Neural Network with Joint Verification and Identification Loss for Person Re-detection