无监督行人重识别新方法，通过姿态变换和聚类提升特征区分度。
Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification
- 先生成姿态扰动数据，再用径向距离聚类优化特征分布。
- 在多个大规模数据集上超越现有最先进方法。
- 适合缺乏标签数据的跨域行人识别场景。
行人重识别（re-ID）旨在解决跨非重叠摄像头匹配同一身份的问题。监督方法依赖难以获取的真实标签，且易受训练数据集偏差影响，难以跨领域扩展。为此，我们提出一种无监督行人重识别方法。在完全未知真实标签的前提下，通过创新的两阶段训练策略增强学习特征的判别能力。第一阶段在专家设计的姿态变换数据集上训练深度网络，该数据集通过对每张原始图像在姿态空间生成多种扰动获得。第二阶段，网络使用提出的判别聚类算法，将相似特征在特征空间中拉近。我们引入一种新颖的径向距离损失，关注特征学习的核心：紧凑簇内低方差、簇间高差异。在多个大规模re-ID数据集上的大量实验表明，该方法优于当前最先进的技术。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。