Abstract
Person re-identification (re-ID) aims to tackle the problem of matching identities across non-overlapping cameras. Supervised approaches require identity information that may be difficult to obtain and are inherently biased towards the dataset they are trained on, making them unscalable across domains. To overcome these challenges, we propose an unsupervised approach to the person re-ID setup. Having zero knowledge of true labels, our proposed method enhances the discriminating ability of the learned features via a novel two-stage training strategy. The first stage involves training a deep network on an expertly designed pose-transformed dataset obtained by generating multiple perturbations for each original image in the pose space. Next, the network learns to map similar features closer in the feature space using the proposed discriminative clustering algorithm. We introduce a novel radial distance loss, that attends to the fundamental aspects of feature learning - compact clusters with low intra-cluster and high inter-cluster variation. Extensive experiments on several large-scale re-ID datasets demonstrate the superiority of our method compared to state-of-the-art approaches.
Abstract (translated)
人员再识别（re-ID）旨在解决跨非重叠摄像头匹配身份的问题。监督方法需要身份信息，这些信息可能难以获取，并且本质上倾向于它们所训练的数据集，使得它们在不同领域中不可扩展。为克服这些挑战，我们提出了一种无监督的人员re-ID设置方法。我们的提议方法对真实标签没有任何先验知识，并通过一种新颖的两阶段训练策略来增强学习特征的区分能力。第一阶段涉及在一个由生成每个原始图像的多个人体姿态变换而得的数据集上训练深度网络。接下来，该网络利用所提出的判别聚类算法，在特征空间中将相似特征映射得更近。我们引入了一种新颖的径向距离损失函数，它关注于特征学习的基本方面——即具有低簇内和高簇间变异性的紧凑簇。在多个大规模re-ID数据集上的广泛实验表明，我们的方法优于最先进的方法。
URL
https://arxiv.org/abs/2411.04255
