← Search

Vedaldi A.

2 accepted papers

2020

A critical analysis of self-supervision, or what we can learn from a single image

ICLR 2020poster

We look critically at popular self-supervision techniques for learning deep convolutional neural networks without manual labels. We show that three different and representative methods, BiGAN, RotNet and DeepCluster, can learn the first few layers of a convolutional network from a single image as we…

Cited by 171SourcecodeScholar