In the field of computer vision, self-supervised learning has emerged as a
method to extract robust features from unlabeled data, where models derive
labels autonomously from the data itself, without the need for manual
annotation. This paper provides a comprehensive review of discriminative
approaches of self-supervised learning within the domain of computer vision,
examining their evolution and current status. Through an exploration of various
methods including contrastive, self-distillation, knowledge distillation,
feature decorrelation, and clustering techniques, we investigate how these
approaches leverage the abundance of unlabeled data. Finally, we have
comparison of self-supervised learning methods on the standard ImageNet
classification benchmark.

计算机视觉领域的自监督学习是从无标签数据中提取强大特征的方法，模型通过自动从数据本身中推导标签而无需人工注释。本文全面回顾了计算机视觉领域内的自监督学习的判别性方法，包括对比、自蒸馏、知识蒸馏、特征去相关化和聚类技术，并研究这些方法如何利用大量的无标签数据。最后，我们对标准的 ImageNet 分类基准上的自监督学习方法进行了比较。