基于支持对挖掘的主动学习行人再识别.

Supervised-learning based person re-identification require a large amount of manual labeled data, which is not applicable in practical deployment. This paper proposes a support pairs active learning（SPAL） re-identification framework to lower the manual labeling cost for large-scale person re-identification. Specifically, this paper build a kind of unsupervised active learning framework, and in this framework it designs a dual uncertainty selection strategy to iteratively discover support pairs and requires human annotations. Afterwards, it introduces a constrained clustering algorithm to propagate the relationships of labeled support pairs to other unlabeled samples. Moreover, a hybrid learning strategy consisting of an unsupervised contrastive loss and a supervised support pairs loss is proposed to learn the discriminative feature representation. On large-scale person re-identification dataset MSMT17, compared with the state-of-the-art method, the labeling cost of the proposed method is reduced by 64%, mAP and Rank1 are increased by 11.0% and 14.9% respectively. Extensive experiments demonstrate that it can effectively lower the labeling cost and is superior to state-of-the-art unsupervised active learning person re-identification methods. [ABSTRACT FROM AUTHOR]