CamStyle: A Novel Data Augmentation Method for Person Re-Identification

Authors:
Publisher website
Google Scholar
Abstract
Person re-identification (re-ID) is cross-camera retrieval task that suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this paper, we explicitly consider this challenge by introducing camera style (CamStyle). CamStyle can serve as a data augmentation approach that reduces the risk of deep network over-fitting and that smooths the camera style disparities. Specifically, with a style transfer model, labeled training images can be style-transferred to each camera, and, along with the original training samples, form the augmented training set. This method, while increasing data diversity against over-fitting, also incurs a considerable level of noise. In the effort to alleviate the impact of noise, the label smooth regularization (LSR) is adopted. The vanilla version of our method (without LSR) performs reasonably well on few-camera systems in which over-fitting often occurs. With LSR, we demonstrate consistent improvement in all systems regardless of the extent of over-fitting. We also report competitive accuracy compared with the state of the art on Market-1501 and DukeMTMC-reID. Importantly, CamStyle can be employed to the challenging problems of one view learning and unsupervised domain adaptation in person re-identification, both of which have critical research and application significance. The former only has labeled data in one camera view and the latter only has labeled data in the source domain. Experiment results show that CamStyle significantly improves the performance of baseline in the two problems. Specially, for unsupervised domain adaptation, CamStyle achieves state-of-the-art accuracy based on a baseline deep re-ID model on Market-1501 and DukeMTMC-reID. Our code is available at: https://github.com/zhunzhong07/CamStyle
Funding Information
  • National Natural Science Foundation of China (61572409, 61876159, 61806172, U1705286, 61571188)
  • Fujian Province 2011 Collaborative Innovation Center of TCM Health Management
  • Collaborative Innovation Center of Chinese Oolong Tea Industry-Collaborative Innovation Center (2011) of Fujian Province
  • Fund for Integration of Cloud Computing and Big Data
  • Innovation of Science and Education
  • Data to Decisions CRC (D2D CRC)
  • Cooperative Research Centre Programme

This publication has 57 references indexed in Scilit: