One of the important Internet-of-Things applications is to use image and video to realize automatic people monitoring, surveillance, tracking, and reidentification (Re-ID). Despite some recent advances, pedestrian Re-ID remains a challenging task. Existing algorithms based on fully supervised learning for it usually requires numerous labeled image and video data, while often ignoring the problem of data imbalance. This work proposes a method based on unlabeled samples generated by cycle generative adversarial networks. For a newly generated unlabeled sample, it learns its pseudorelationship between unlabeled samples and labeled ones in a low-dimensional space by using a self-paced learning approach. Then, these unlabeled ones having pseudo-relationship with labeled ones are added in a training set to better mine discriminative information between positive and negative samples, which is in turn used to learn a more effective metric. We name this method as a semi-supervised learning approach based on the built pseudopairwise relations between labeled data and unlabeled one. It can greatly enhance the performance of pedestrian Re-ID in case of insufficient labeled images. By using only about 10% labeled images in a given database, the proposed method obtains higher accuracy than state-of-the-art supervised learning methods using all labeled ones, e.g., deep-learning ones, thus greatly advancing the field of pedestrian Re-ID.

中文翻译：

---

一种新颖的行人重新识别半监督学习方法


物联网的重要应用之一是利用图像和视频实现人员自动监控、监视、跟踪和重新识别（Re-ID）。尽管最近取得了一些进展，行人重新识别仍然是一项具有挑战性的任务。现有的基于完全监督学习的算法通常需要大量带标签的图像和视频数据，而往往忽略了数据不平衡的问题。这项工作提出了一种基于循环生成对抗网络生成的未标记样本的方法。对于新生成的未标记样本，它通过使用自定进度的学习方法来学习低维空间中未标记样本和标记样本之间的伪关系。然后，将这些与标记样本具有伪关系的未标记样本添加到训练集中，以更好地挖掘正样本和负样本之间的判别信息，进而用于学习更有效的度量。我们将这种方法称为一种半监督学习方法，基于标记数据和未标记数据之间建立的伪配对关系。在标记图像不足的情况下，可以大大增强行人Re-ID的性能。通过仅使用给定数据库中约 10% 的标记图像，所提出的方法比使用所有标记图像（例如深度学习图像）的最先进的监督学习方法获得了更高的准确性，从而极大地推进了行人识别领域-ID。