Towards Fewer Labels: Support Pair Active Learning for Person Re-identification

TL;DR

This paper introduces a Support Pair Active Learning framework that reduces manual labeling in person re-identification by selecting the most informative pairs and propagating their relationships, improving efficiency and performance.

Contribution

It proposes a novel dual uncertainty selection strategy and a constrained clustering algorithm for effective support pair selection and relationship propagation in active learning.

Findings

Outperforms state-of-the-art active learning methods on large-scale benchmarks.

Effectively reduces labeling costs while maintaining high re-id accuracy.

Demonstrates the benefit of support pair propagation in discriminative feature learning.

Abstract

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.