论文标题
无监督人员重新识别的信心引导的质心
Confidence-guided Centroids for Unsupervised Person Re-Identification
论文作者
论文摘要
无监督的人重新识别(REID)旨在培训功能提取器以进行身份检索而无需利用身份标签。由于对不完善的聚类结果的盲目信任,学习不可避免地被不可靠的伪标签误导。尽管已经通过以前的作品研究了伪标签的完善,但它们通常利用辅助信息,例如相机ID和身体部位预测。这项工作探讨了簇的内部特征,以完善伪标签。为此,提出了信心引导的质心(CGC),以提供可靠的集群原型用于特征学习。由于具有较高置信度的样本仅参与质心的形成,因此低信任样品的身份信息,即边界样本,不太可能有助于相应的质心。鉴于新的质心,当前的学习方案,在该方案中,样本被强制从其指定的质心学习,这是不明智的。为了纠正这种情况,我们建议使用信心引导的伪标签(CGL),该标签(CGL)使样本不仅可以接近最初分配的质心,而且可以接触其他可能嵌入其身份信息的质心。在置信度引导的质心和标签上,我们的方法可以在很大程度上利用辅助信息的最先进的伪标签改进作品,甚至均优于最先进的伪标签。
Unsupervised person re-identification (ReID) aims to train a feature extractor for identity retrieval without exploiting identity labels. Due to the blind trust in imperfect clustering results, the learning is inevitably misled by unreliable pseudo labels. Albeit the pseudo label refinement has been investigated by previous works, they generally leverage auxiliary information such as camera IDs and body part predictions. This work explores the internal characteristics of clusters to refine pseudo labels. To this end, Confidence-Guided Centroids (CGC) are proposed to provide reliable cluster-wise prototypes for feature learning. Since samples with high confidence are exclusively involved in the formation of centroids, the identity information of low-confidence samples, i.e., boundary samples, are NOT likely to contribute to the corresponding centroid. Given the new centroids, current learning scheme, where samples are enforced to learn from their assigned centroids solely, is unwise. To remedy the situation, we propose to use Confidence-Guided pseudo Label (CGL), which enables samples to approach not only the originally assigned centroid but other centroids that are potentially embedded with their identity information. Empowered by confidence-guided centroids and labels, our method yields comparable performance with, or even outperforms, state-of-the-art pseudo label refinement works that largely leverage auxiliary information.