Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well understood, the field still lacks widely accepted best practices for replicating this success on other datasets. As a first step in this direction, we study contrastive self-supervised learning on four diverse large-scale datasets. By looking through the lenses of data quantity, data domain, data quality, and task granularity, we provide new insights into the necessary conditions for successful self-supervised learning. Our key findings include observations such as: (i) the benefit of additional pretraining data beyond 500k images is modest, (ii) adding pretraining images from another domain does not lead to more general representations, (iii) corrupted pretraining images have a disparate impact on supervised and self-supervised pretraining, and (iv) contrastive learning lags far behind supervised learning on fine-grained visual classification tasks.

本文研究了自监督学习在四个不同的大规模数据集上的对比学习方法，通过数据量、数据领域、数据质量和任务粒度，得出了有关成功自监督学习所需条件的新见解，其中包括：(i) 除500k张图像外，额外的预训练数据的收益有限；(ii) 添加来自另一个领域的预训练图像不会产生更通用的表示。(iii) 比较学习在细粒度的视觉分类任务中远远落后于监督学习。

对比度视觉表征学习何时有效？