Learning adaptively from the unknown for few-example video person re-ID
arXiv:1908.09340
Abstract
This paper mainly studies one-example and few-example video person re-identification. A multi-branch network PAM that jointly learns local and global features is proposed. PAM has high accuracy, few parameters and converges fast, which is suitable for few-example person re-identification. We iteratively estimates labels for unlabeled samples, incorporates them into training sets, and trains a more robust network. We propose the static relative distance sampling(SRD) strategy based on the relative distance between classes. For the problem that SRD can not use all unlabeled samples, we propose adaptive relative distance sampling (ARD) strategy. For one-example setting, We get 89.78\%, 56.13\% rank-1 accuracy on PRID2011 and iLIDS-VID respectively, and 85.16\%, 45.36\% mAP on DukeMTMC and MARS respectively, which exceeds the previous methods by large margin.
arXiv commentThis is a draft and there are many places to be revised
References in corpus (6)
- Matching Networks for One Shot Learning
- Harmonious Attention Network for Person Re-Identification
- Deep Metric Learning for Practical Person Re-Identification
- Quality Aware Network for Set to Set Recognition
- Video-based Person Re-identification with Accumulative Motion Context
- Attention-based Few-Shot Person Re-identification Using Meta Learning