Towards Fewer Labels: Support Pair Active Learning for Person Re-identification
This work addresses the labeling burden in person re-identification for practical deployment, representing an incremental improvement in active learning techniques.
The paper tackles the high manual labeling cost in supervised person re-identification by proposing a Support Pair Active Learning framework, which reduces labeling effort by selecting and propagating informative support pairs, achieving superior performance over state-of-the-art active learning methods on large-scale benchmarks.
Supervised-learning based person re-identification (re-id) require a large amount of manual labeled data, which is not applicable in practical re-id deployment. In this work, we propose a Support Pair Active Learning (SPAL) framework to lower the manual labeling cost for large-scale person reidentification. The support pairs can provide the most informative relationships and support the discriminative feature learning. Specifically, we firstly design a dual uncertainty selection strategy to iteratively discover support pairs and require human annotations. Afterwards, we introduce 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 pair loss is proposed to learn the discriminative re-id feature representation. The proposed overall framework can effectively lower the labeling cost by mining and leveraging the critical support pairs. Extensive experiments demonstrate the superiority of the proposed method over state-of-the-art active learning methods on large-scale person re-id benchmarks.