Learning adaptively from the unknown for few-example video person re-ID

TL;DR

This paper introduces a multi-branch network with adaptive sampling strategies for effective few-example video person re-identification, achieving state-of-the-art accuracy with high efficiency.

Contribution

It proposes a novel multi-branch network PAM and adaptive relative distance sampling strategies for improved few-example video person re-ID.

Findings

Achieved 89.78% rank-1 accuracy on PRID2011

Achieved 56.13% rank-1 accuracy on iLIDS-VID

Significantly outperformed previous methods in accuracy

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.