Supervised person re-identification (re-id) approaches require a large amount of pairwise manual labeled data, which is not applicable in most real-world scenarios for re-id deployment. On the other hand, unsupervised re-id methods rely on unlabeled data to train models but performs poorly compared with supervised re-id methods. In this work, we aim to combine unsupervised re-id learning with a small number of human annotations to achieve a competitive performance. Towards this goal, we present a Unsupervised Clustering Active Learning (UCAL) re-id deep learning approach. It is capable of incrementally discovering the representative centroid-pairs and requiring human annotate them. These few labeled representative pairwise data can improve the unsupervised representation learning model with other large amounts of unlabeled data. More importantly, because the representative centroid-pairs are selected for annotation, UCAL can work with very low-cost human effort. Extensive experiments demonstrate the superiority of the proposed model over state-of-the-art active learning methods on three re-id benchmark datasets.
翻译:在这项工作中,我们的目标是将未经监督的再定位(再定位)方法与少量人类说明结合起来,以取得有竞争力的性能。为了实现这一目标,我们提出了一种未经监督的分组主动学习(UCAL)再定位深层学习方法。它能够逐步发现有代表性的中位体型,并要求人类进行批注。这些为数不多的有代表性的配对数据可以用其他大量无标签的数据来改进未经监督的代言学习模式。更重要的是,由于代言的中位体型和批量的人类说明是被选作注解的,因此,UCAL可以以非常低成本的人类努力来工作。广泛的实验表明,拟议的模型优于三种重定位基准数据集上的最新主动学习方法。