Learning adaptively from the unknown for few-example video person re-ID
It addresses the problem of limited labeled data for video-based person re-identification, which is crucial for surveillance and security applications, with incremental improvements in sampling strategies.
This paper tackles few-example video person re-identification by proposing a multi-branch network and adaptive sampling strategies, achieving rank-1 accuracies of 89.78% on PRID2011 and 56.13% on iLIDS-VID, and mAP scores of 85.16% on DukeMTMC and 45.36% on MARS, significantly exceeding previous methods.
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.