Random style transfer for person re-identification with one example

Abstract

Person re-identification with only one labeled image for each identify can not eliminate the style variations of different cameras in the same dataset. In this paper, we propose a random style transfer strategy that randomly transforms the labeled images on the one-example person re-identification task. In this strategy, we focus on twofolds: 1) Randomly transform the camera style of labeled images and unlabeled images during the training stage and 2) use the average feature of labeled data and its camera style transform data to estimate pseudo label on unlabeled data. Notably, our strategy exhibits state-of-the-art performance on large-scale image datasets and its Rank-1 accuracy outperforms the state-of-the-art method by 10.3% points on Market-1501, and 8.4% points on DukeMTMC-reID.

Keywords

• one-example
• person re-identification
• semi-supervised learning
• style transfer