Person Transfer GAN to Bridge Domain Gap for Person Re-identification

TLDR

Despite recent advances in person re‑identification, challenges such as complex scenes, lighting variations, pose changes, large identity sets, and domain gaps between datasets still hinder robust performance. The study introduces the MSMT171 dataset and proposes the PTGAN to bridge domain gaps and reduce annotation costs in person re‑identification. PTGAN employs a generative adversarial framework to translate person images from a source domain to a target domain, leveraging the MSMT171 dataset’s extensive multi‑camera, multi‑lighting recordings and 4,101 identities for training. Experiments demonstrate that PTGAN significantly reduces the domain gap, enabling better transfer of training data to new testing domains.

Abstract

Although the performance of person Re-Identification (ReID) has been significantly boosted, many challenging issues in real scenarios have not been fully investigated, e.g., the complex scenes and lighting variations, viewpoint and pose changes, and the large number of identities in a camera network. To facilitate the research towards conquering those issues, this paper contributes a new dataset called MSMT171 with many important features, e.g., 1) the raw videos are taken by an 15-camera network deployed in both indoor and outdoor scenes, 2) the videos cover a long period of time and present complex lighting variations, and 3) it contains currently the largest number of annotated identities, i.e., 4,101 identities and 126,441 bounding boxes. We also observe that, domain gap commonly exists between datasets, which essentially causes severe performance drop when training and testing on different datasets. This results in that available training data cannot be effectively leveraged for new testing domains. To relieve the expensive costs of annotating new training samples, we propose a Person Transfer Generative Adversarial Network (PTGAN) to bridge the domain gap. Comprehensive experiments show that the domain gap could be substantially narrowed-down by the PTGAN.