Semantic Consistency and Identity Mapping Multi-Component Generative Adversarial Network for Person Re-Identification
This addresses the problem of robust person re-identification for surveillance and security applications, but it is incremental as it builds on existing GAN and network approaches.
The paper tackles the challenge of person re-identification in real-world environments with variations like lighting and pose by proposing SC-IMGAN, which uses style adaptation and novel losses to generate realistic images, and a joint network trained with generated and real images, achieving state-of-the-art results on six datasets.
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.