Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification
Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification
复制标题
DOI：
10.1109/cvpr.2019.00375
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Q. Yang;Hong-Xing Yu;Ancong Wu;Weishi Zheng
中科院分区：
文献类型：
--
作者：
Q. Yang;Hong-Xing Yu;Ancong Wu;Weishi Zheng
虽然判别性局部特征已被证明可以有效解决人员重新识别问题，但它们仅限于在完全成对标记数据上进行训练，而获得这种数据的成本很高。在这项工作中，我们通过提出一种基于补丁的无监督学习框架来克服这个问题，以便从补丁而不是整个图像中学习判别特征。基于补丁的学习利用补丁之间的相似性来学习判别模型。具体来说，我们开发了一个 PatchNet 来从特征图中选择补丁并学习这些补丁的判别特征。为了为 PatchNet 在未标记数据集上学习判别性补丁特征提供有效指导，我们提出了一种无监督的基于补丁的判别性特征学习损失。此外，我们设计了图像级特征学习损失，以利用同一图像的所有补丁特征作为 PatchNet 的图像级指导。大量的实验验证了我们的方法在无人监督的行人重识别方面的优越性。我们的代码可在 https://github.com/QizeYang/PAUL 获取。
While discriminative local features have been shown effective in solving the person re-identification problem, they are limited to be trained on fully pairwise labelled data which is expensive to obtain. In this work, we overcome this problem by proposing a patch-based unsupervised learning framework in order to learn discriminative feature from patches instead of the whole images. The patch-based learning leverages similarity between patches to learn a discriminative model. Specifically, we develop a PatchNet to select patches from the feature map and learn discriminative features for these patches. To provide effective guidance for the PatchNet to learn discriminative patch feature on unlabeled datasets, we propose an unsupervised patch-based discriminative feature learning loss. In addition, we design an image-level feature learning loss to leverage all the patch features of the same image to serve as an image-level guidance for the PatchNet. Extensive experiments validate the superiority of our method for unsupervised person re-id. Our code is available at https://github.com/QizeYang/PAUL.