论文标题
是什么使对比度学习有很好的看法？
What Makes for Good Views for Contrastive Learning?
论文作者
论文摘要
在数据的多种观点之间，对比度学习在自我监督的表示学习领域中实现了最先进的表现。尽管取得了成功，但对不同观点选择的影响的研究较少。在本文中，我们使用理论和经验分析来更好地了解视图选择的重要性，并认为我们应该在视图之间减少互信息（MI），同时保持与任务相关的信息完整。为了验证这一假设，我们设计了无监督和半监督的框架，以减少其MI来学习有效的观点。我们还将数据增加视为减少MI的一种方式，并表明增加数据增加确实会导致MI降低并提高下游分类的准确性。作为副产品，我们可以针对Imagenet分类的无监督预训练（73 \％$ $ $ $ $ $ top-top-1 $ resnet-50）实现新的最新精度。此外，将我们的模型转移到Pascal VOC对象检测和可可实例分段始终优于监督预训练的表现。代码：http：//github.com/hobbitlong/pycontrast
Contrastive learning between multiple views of the data has recently achieved state of the art performance in the field of self-supervised representation learning. Despite its success, the influence of different view choices has been less studied. In this paper, we use theoretical and empirical analysis to better understand the importance of view selection, and argue that we should reduce the mutual information (MI) between views while keeping task-relevant information intact. To verify this hypothesis, we devise unsupervised and semi-supervised frameworks that learn effective views by aiming to reduce their MI. We also consider data augmentation as a way to reduce MI, and show that increasing data augmentation indeed leads to decreasing MI and improves downstream classification accuracy. As a by-product, we achieve a new state-of-the-art accuracy on unsupervised pre-training for ImageNet classification ($73\%$ top-1 linear readout with a ResNet-50). In addition, transferring our models to PASCAL VOC object detection and COCO instance segmentation consistently outperforms supervised pre-training. Code:http://github.com/HobbitLong/PyContrast
