Exploit the Unknown Gradually: One-Shot Video-Based Person Re-Identification by Stepwise Learning

Yu Wu, Yutian Lin, Xuanyi Dong, Yan Yan, Wanli Ouyang, Yi Yang

Abstract: We focus on the one-shot learning for video-based person re-Identification (re-ID). Unlabeled tracklets for the person re-ID tasks can be easily obtained by pre- processing, such as pedestrian detection and tracking. In this paper, we propose an approach to exploiting unla- beled tracklets by gradually but steadily improving the dis- criminative capability of the Convolutional Neural Network (CNN) feature representation via stepwise learning. We first initialize a CNN model using one labeled tracklet for each identity. Then we update the CNN model by the following two steps iteratively: 1. sample a few candidates with most reliable pseudo labels from unlabeled tracklets; 2. update the CNN model according to the selected data. Instead of the static sampling strategy applied in existing works, we propose a progressive sampling method to increase the number of the selected pseudo-labeled candidates step by step. We systematically investigate the way how we should select pseudo-labeled tracklets into the training set to make the best use of them. Notably, the rank-1 accuracy of our method outperforms the state-of-the-art method by 21.46 points (absolute, i.e., 62.67% vs. 41.21%) on the MARS dataset, and 16.53 points on the DukeMTMC-VideoReID dataset.