Camera Style Adaptation for Person Re-identification

Publication Type:
Conference Proceeding
Citation:
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, pp. 5157 - 5166
Issue Date:
2018-12-14
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
1711.10295.pdfAccepted Manuscript version2.65 MB
Adobe PDF
© 2018 IEEE. Being a cross-camera retrieval task, person re-identification 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) adaptation. CamStyle can serve as a data augmentation approach that smooths the camera style disparities. Specifically, with CycleGAN, 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. Code is available at: Https://github.com/zhunzhong07/CamStyle.
Please use this identifier to cite or link to this item: