TL;DR该研究提出了一种名为 Contrastive Learning with Stronger Augmentations(CLSA)的新的对比学习方法,利用数据扩增引入样本多样性,从而提高检索能力,实验结果表明该方法在 ImageNet 数据集上的表现接近有监督结果。
Abstract
representation learning has significantly been developed with the advance of
contrastive learning methods. Most of those methods have benefited from various
data augmentations that are carefully designated to mai