A GAN-Based Self-Training Framework for Unsupervised Domain Adaptive Person Re-Identification

Journal of Imaging

Zhiqin Zhu¹  Sixin Chen²  Yuanyuan Li²  Ruihua Cai³  Guanqiu Qi⁴  Matthew Haner⁵ 

[1] College of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;College of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;Computer Engineering Department, San Jose State University, San Jose, CA 95192, USA;Computer Information Systems Department, State University of New York at Buffalo State, Buffalo, NY 14222, USA;Department of Mathematics & Computer and Information Science, Mansfield University of Pennsylvania, Mansfield, PA 16933, USA;

关键词: person re-ID;    domain shift;    style transfer;    self-training;   

DOI  :  10.3390/jimaging7040062

来源: DOAJ

【 摘 要 】

As a crucial task in surveillance and security, person re-identification (re-ID) aims to identify the targeted pedestrians across multiple images captured by non-overlapping cameras. However, existing person re-ID solutions have two main challenges: the lack of pedestrian identification labels in the captured images, and domain shift issue between different domains. A generative adversarial networks (GAN)-based self-training framework with progressive augmentation (SPA) is proposed to obtain the robust features of the unlabeled data from the target domain, according to the preknowledge of the labeled data from the source domain. Specifically, the proposed framework consists of two stages: the style transfer stage (STrans), and self-training stage (STrain). First, the targeted data is complemented by a camera style transfer algorithm in the STrans stage, in which CycleGAN and Siamese Network are integrated to preserve the unsupervised self-similarity (the similarity of the same image between before and after transformation) and domain dissimilarity (the dissimilarity between a transferred source image and the targeted image).  Second, clustering and classification are alternately applied to enhance the model performance progressively in the STrain stage, in which both global and local features of the target-domain images are obtained. Compared with the state-of-the-art methods, the proposed method achieves the competitive accuracy on two existing datasets.

【 授权许可】

Unknown