The Exemplar Memory (EM) design has shown its effectiveness in facilitating the unsupervised person re-identification (RE-ID). However, there are obvious defects in the update strategies with most existing results, such as the inability to eliminate static errors and ensure convergence stability of learning. To address these issues, in this paper, we propose a novel center feature learning scheme to improve the update strategies of the traditional EM design for unsupervised RE-ID problems. First, the EM module is regarded as a center feature of a cluster of images, then the goal is transformed into pulling the similar images close to while pushing the dissimilar images away from the center feature space. Second, in order to provide effective guidelines on reducing static errors, we propose an error-memory module to improve the central feature learning performances. In addition, an error-prediction module is designed as well to ensure the stability of convergence. Besides, a camera-invariance learning strategy is also introduced to further improve the proposed algorithm. Finally, extensive comparative experiments are conducted on Market-1501 and DukeMTMC-reID datasets to demonstrate the effectiveness and improvements of the proposed method over existing results. The code of this work is available at https://github.com/binquanwang/CFL_master.

中文翻译：

---

无监督人员重新识别的中心特征学习

示例记忆 (EM) 设计已显示出其在促进无监督人员重新识别 (RE-ID) 方面的有效性。然而，大多数现有结果的更新策略都存在明显的缺陷，例如无法消除静态错误并确保学习的收敛稳定性。为了解决这些问题，在本文中，我们提出了一种新颖的中心特征学习方案，以改进传统 EM 设计对无监督 RE-ID 问题的更新策略。首先，将 EM 模块视为一组图像的中心特征，然后将目标转化为将相似图像拉近，同时将不相似图像推离中心特征空间。其次，为了提供有效的减少静态误差的指导方针，我们提出了一个错误记忆模块来提高中心特征学习的性能。此外，还设计了一个误差预测模块来保证收敛的稳定性。此外，还引入了相机不变性学习策略以进一步改进所提出的算法。最后，在 Market-1501 和 DukeMTMC-reID 数据集上进行了广泛的比较实验，以证明所提出的方法对现有结果的有效性和改进。这项工作的代码可在 https://github.com/binquanwang/CFL_master 获得。在 Market-1501 和 DukeMTMC-reID 数据集上进行了广泛的比较实验，以证明所提出的方法对现有结果的有效性和改进。这项工作的代码可在 https://github.com/binquanwang/CFL_master 获得。在 Market-1501 和 DukeMTMC-reID 数据集上进行了广泛的比较实验，以证明所提出的方法对现有结果的有效性和改进。这项工作的代码可在 https://github.com/binquanwang/CFL_master 获得。