Domain Adaptive Person Re-Identification via Camera Style Generation and Label Propagation

• Published in: IEEE transactions on information forensics and security Vol. 15; pp. 1290 - 1302
• Main Authors: Ren, Chuan-Xian, Liang, Bohua, Ge, Pengfei, Zhai, Yiming, Lei, Zhen
• Format: Journal Article
• Language: English
• Published: New York IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Adaptation models; Algorithms; camera style transfer; Cameras; distribution discrepancy; domain adaptation; Generative adversarial networks; Generators; Identification; Identification methods; Labeling; Labels; Metric space; Person re-identification; soft-labeling; Task analysis; Training
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2019.2939750

Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping labels challenge that the source domain and the target domain have entirely different persons further increases the re-identification difficulty. In this paper, we propose a novel algorithm to narrow such domain gaps. We derive a camera style adaptation framework to learn the style-based mappings between different camera views, from the target domain to the source domain, and then we can transfer the identity-based distribution from the source domain to the target domain on the camera level. Target camera variations can be captured by the style adaptation method, thus, the re-identification model trained on the target domain can learn target camera-invariant features better. It indicates that the style translator approximates an appropriate metric space for improving feature matching. To overcome the non-overlapping labels challenge and guide the person re-identification model to narrow the gap further, an efficient and effective soft-labeling method is proposed to mine the intrinsic local structure of the target domain through building the connection between GAN-translated source domain and the target domain. Experiment results conducted on real benchmark datasets indicate that our method gets state-of-the-art results.