In many machine learning applications, labeling datasets can be an arduous and time-consuming task. Although research has shown that semi-supervised learning techniques can achieve high accuracy with very few labels within the field of computer vision, little attention has been given to how images within a dataset should be selected for labeling. In this paper, we propose a novel approach based on well-established self-supervised learning, clustering, and manifold learning techniques that address this challenge of selecting an informative image subset to label in the first instance, which is known as the cold-start or unsupervised selective labelling problem. We test our approach using several publicly available datasets, namely CIFAR10, Imagenette, DeepWeeds, and EuroSAT, and observe improved performance with both supervised and semi-supervised learning strategies when our label selection strategy is used, in comparison to random sampling. We also obtain superior performance for the datasets considered with a much simpler approach compared to other methods in the literature.

本文提出了一种新方法，基于半监督学习、自监督学习、聚类和流形学习技术解决了冷启动或无监督选择标签问题，该方法在选择信息图像的子集进行标记时取得了良好的结果，通过我们的标签选择策略在 CIFAR10，Imagenette， DeepWeeds 和 EuroSAT等公开数据集上进行测试，与随机采样相比，采用我们的标签选择策略使用时，监督和半监督学习策略的性能都有所提高，相比文献中的其他方法，对于所考虑的数据集，我们也获得了更好的性能。

Cold PAWS：无监督类别发现和冷启动问题