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

TL;DR

This paper introduces a new large-scale dataset for person re-identification and proposes a PTGAN model to effectively bridge domain gaps between datasets, improving cross-domain re-identification performance.

Contribution

The paper presents MSMT17, a comprehensive dataset for person ReID, and introduces PTGAN, a novel generative model to reduce domain discrepancies in re-identification tasks.

Findings

MSMT17 dataset contains 4,101 identities and 126,441 bounding boxes.

PTGAN significantly narrows the domain gap between different datasets.

Experimental results demonstrate improved cross-dataset ReID performance.

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 MSMT17 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.