Camera Style Adaptation for Person Re-identification
arXiv:1711.10295
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.
arXiv commentTo appear in CVPR 2018
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Deep Residual Learning for Image Recognition
- In Defense of the Triplet Loss for Person Re-Identification
- Person Re-identification: Past, Present and Future
- Improving Person Re-identification by Attribute and Identity Learning
- A Discriminatively Learned CNN Embedding for Person Re-identification
- Random Erasing Data Augmentation
- Rethinking the Inception Architecture for Computer Vision
- Pedestrian Alignment Network for Large-scale Person Re-identification
- PersonNet: Person Re-identification with Deep Convolutional Neural Networks
- SVDNet for Pedestrian Retrieval
- Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
- Style Aggregated Network for Facial Landmark Detection