# S4L: Self-Supervised Semi-Supervised Learning

## TL;DR

This paper introduces a unified framework combining self-supervised and semi-supervised learning for image classification, leading to new methods that outperform existing approaches and achieve state-of-the-art results on large-scale datasets.

## Contribution

It proposes the self-supervised semi-supervised learning framework and derives two novel methods that improve semi-supervised image classification performance.

## Key findings

- New semi-supervised methods outperform baselines.
- Joint training achieves state-of-the-art on ILSVRC-2012 with 10% labels.
- Framework effectively leverages self-supervised representations.

## Abstract

This work tackles the problem of semi-supervised learning of image classifiers. Our main insight is that the field of semi-supervised learning can benefit from the quickly advancing field of self-supervised visual representation learning. Unifying these two approaches, we propose the framework of self-supervised semi-supervised learning and use it to derive two novel semi-supervised image classification methods. We demonstrate the effectiveness of these methods in comparison to both carefully tuned baselines, and existing semi-supervised learning methods. We then show that our approach and existing semi-supervised methods can be jointly trained, yielding a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels.