S4L: Self-Supervised Semi-Supervised Learning
This work addresses the problem of improving image classification with limited labeled data for researchers and practitioners in computer vision, representing an incremental advancement by unifying existing approaches.
The paper tackled semi-supervised learning for image classification by integrating self-supervised representation learning, proposing two novel methods that achieved a new state-of-the-art result on semi-supervised ILSVRC-2012 with 10% of labels.
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.