S4L: Self-Supervised Semi-Supervised Learning

被引：632

作者：

Zhai, Xiaohua ^{[1
]}

Oliver, Avital ^{[1
]}

Kolesnikov, Alexander ^{[1
]}

Beyer, Lucas ^{[1
]}

机构：

[1] Google Res, Brain Team, Mountain View, CA 94043 USA

来源：

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) | 2019年

关键词：

D O I：

10.1109/ICCV.2019.00156

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 ((SL)-L-4) 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 (SL)-L-4 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.

引用

页码：1476 / 1485

页数：10