Semi-supervised learning for person re-identification based on style-transfer-generated data by CycleGANs

Shangdong Zhu, Yunzhou Zhang, Sonya Coleman, Song Wang, Ruilong Li, Shuangwei Liu

Research output: Contribution to journalArticlepeer-review

Abstract

Person re-identification (re-ID) is an exceedingly significant branch in the field of computer vision, especially for video surveillance. It is still a challenge to obtain more labeled training data and use them reasonably for more precise matching, though the person re-ID performance has been improved significantly. In order to solve this challenge, this study proposes a semi-supervised learning algorithm for data augmentation, the style-transfer-generated data as an extra class (STGDEC), which is aided by the Cycle-Consistent Adversarial Networks (CycleGANs) in generating extra unlabeled training data. Specifically, the algorithm firstly trains the CycleGANs and Deep Convolutional Generative Adversarial Networks so as to generate large amounts of unlabeled data. Secondly, we propose an adaptive receptive field module to expand the size of receptive fields and select the appropriate receptive field features dynamically in order to learn more contextual information and discriminative feature representation and embed the module in the backbone network easily. Thirdly, we use the combination of label smoothing regularization for outliers and an extra class loss to regularize the generated data and encourage the network not to be too confident to the ground-truth. Finally, this paper proposes three training strategies for the combination of standard dataset and generated samples. Comprehensive experiments based on the STGDEC are conducted, and these results show that the proposed algorithm gains a significant improvement over the baseline, the Basel. + LSRO and state-of-the-art approaches of person re-ID in many cases.

Original languageEnglish
Article number122
Pages (from-to)1-16
Number of pages16
JournalMachine Vision and Applications
Volume32
Issue number6
Early online date1 Oct 2021
DOIs
Publication statusE-pub ahead of print - 1 Oct 2021

Bibliographical note

Funding Information:
This work is partly supported by National Natural Science Foundation of China (No. 61973066), Distinguished Creative Talent Program of Liaoning Colleges and Universities (LR2019027), and Fundamental Research Funds for the Central Universities (N182608004, N2004022).

Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Keywords

  • Adaptive receptive field module
  • Data augmentation
  • Generative adversarial network
  • Person re-identification
  • Semi-supervised learning

Fingerprint

Dive into the research topics of 'Semi-supervised learning for person re-identification based on style-transfer-generated data by CycleGANs'. Together they form a unique fingerprint.

Cite this