Camera Style Adaptation for Person Re-identification

Code

• github.com/zhunzhong07/CamStyle
  OfficialIn paperpytorch★ 0
• github.com/Demonhesusheng/Reid
  pytorch★ 0
• github.com/taroogura/Person_reID_baseline_pytorch
  pytorch★ 0
• github.com/AndlollipopFU/PCB
  pytorch★ 0
• github.com/NIRVANALAN/reid_baseline
  pytorch★ 0
• github.com/lsh110600/person_re_id
  pytorch★ 0
• github.com/ivychill/reid
  pytorch★ 0
• github.com/Proxim123/person-reID-No1-
  pytorch★ 0
• github.com/jiangsikai/Person_reID_baseline_pytorch
  pytorch★ 0
• github.com/BonaventureR/person-reid
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions