论文标题
标签更少：支持人重新识别的主动学习
Towards Fewer Labels: Support Pair Active Learning for Person Re-identification
论文作者
论文摘要
基于监督学习的人重新识别（RE-ID）需要大量的手动标记数据，这不适用于实际重新部署。在这项工作中，我们提出了一个支持对积极学习（SPAL）框架，以降低大规模重新识别的手动标签成本。支持对可以提供最有用的关系，并支持歧视性特征学习。具体而言，我们首先设计了双重不确定性选择策略，以迭代地发现支持对并需要人类注释。之后，我们引入了一种约束的聚类算法，以传播标记的支持对与其他未标记样本的关系。此外，提出了一种由无监督的对比损失和监督支持对损失组成的混合学习策略，以学习歧视性重新ID特征表示。提出的整体框架可以通过采矿和利用关键支撑对有效地降低标签成本。广泛的实验证明了所提出的方法优于大规模重新ID基准测试的最先进的主动学习方法。
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.
