Self-Guided Hard Negative Generation for Unsupervised Person Re-Identification

Abstract

Recent unsupervised person re-identification (re-ID) methods mostly apply pseudo labels from clustering algorithms as supervision signals. Despite great success, this fashion is very likely to aggregate different identities with similar appearances into the same cluster. As a result, the truly hard negative samples, playing an important role in training re-ID models, are significantly reduced. To alleviate this problem, we propose a self-guided hard negative generation method for unsupervised person re-ID. Specifically, a joint framework is developed which incorporates a hard negative generation network (HNGN) and a re-ID network. To continuously generate harder negative samples to provide effective supervisions in the contrastive learning, the two networks are alternately trained in an adversarial manner to improve each other. In detail, the re-ID network guides HNGN to generate challenging data, and HNGN in turn enforces the re-ID network to enhance discrimination ability. During inference, the performance of re-ID network is improved without introducing any extra parameters. Extensive experiments demonstrate that the proposed method significantly outperforms a strong baseline and also achieves better results than state-of-the-art methods.