In this paper, we study the unsupervised person re-identification (re-ID) problem, which does not require any annotation information. Our approach considers three aspects in unsupervised re-ID task, i.e., variance across various cameras, label allocation to unlabeled images and hard negative mining. First, an unsupervised style transfer model is adopted to generate style-transferred images with different camera styles, which contributes to reduce the variance across various cameras. Then we apply k-reciprocal encoding method to obtain k-reciprocal nearest neighbors. According to the feature similarity of the probe person with its neighbors, soft pseudo labels are allocated to the probe person iteratively. Due to lack of annotation information to pairwise images, we propose the k-reciprocal nearest neighbors loss (KNNL) to learn discriminative features. Furthermore, a hard negative mining strategy is adopted to improve the accuracy and robustness of our framework. We conduct experiments on three large-scale datasets: Market-1501, DukeMTMC-reID and MSMT17. Results show that our method not only outperforms the state-of-the-art unsupervised re-ID approaches, but also is superior to unsupervised domain adaptation methods (UDA) and semi-supervised learning methods.

在本文中，我们研究了不需要任何注释信息的无监督人员重新识别（re-ID）问题。我们的方法考虑了无监督 re-ID 任务的三个方面，即各种相机之间的差异、未标记图像的标签分配和硬负挖掘。首先，采用无监督的风格转移模型来生成具有不同相机风格的风格转移图像，这有助于减少各种相机之间的差异。然后我们应用k -reciprocal 编码方法来获得k -reciprocal 最近邻。根据探测人物与其邻居的特征相似度，迭代地为探测人物分配软伪标签。由于缺乏成对图像的注释信息，我们提出了k -reciprocal 最近邻损失 (KNNL) 来学习判别特征。此外，采用硬负挖掘策略来提高我们框架的准确性和鲁棒性。我们在三个大规模数据集上进行了实验：Market-1501、DukeMTMC-reID 和 MSMT17。结果表明，我们的方法不仅优于最先进的无监督 re-ID 方法，而且优于无监督域适应方法 (UDA) 和半监督学习方法。