S4L: Self-Supervised Semi-Supervised Learning

Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov, Lucas Beyer; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 1476-1485

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 (S4L) 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 S4L 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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Zhai_2019_ICCV,
author = {Zhai, Xiaohua and Oliver, Avital and Kolesnikov, Alexander and Beyer, Lucas},
title = {S4L: Self-Supervised Semi-Supervised Learning},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}