Camera Style Adaptation for Person Re-identification
Citations Over TimeTop 1% of 2018 papers
Abstract
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.
Related Papers
- → PCA-subspace method — Is it good enough for network-wide anomaly detection(2012)27 cited
- → Large scale hand-written character recognition system using subspace method(2002)5 cited
- Fast algorithm for robust subspace recovery.(2014)
- → A novel algorithm of subspace tracking based on the PAST method(2011)
- Determination of the Evacuation Route by Subspace Model(2007)