Billion-scale semi-supervised learning for image classification
This work addresses the challenge of enhancing standard architectures like ResNet-50 for image classification, providing significant gains in accuracy, though it is incremental as it builds on existing teacher/student paradigms.
The paper tackled the problem of improving image classification performance using semi-supervised learning with up to 1 billion unlabelled images, resulting in a vanilla ResNet-50 achieving 81.2% top-1 accuracy on ImageNet.
This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Our main goal is to improve the performance for a given target architecture, like ResNet-50 or ResNext. We provide an extensive analysis of the success factors of our approach, which leads us to formulate some recommendations to produce high-accuracy models for image classification with semi-supervised learning. As a result, our approach brings important gains to standard architectures for image, video and fine-grained classification. For instance, by leveraging one billion unlabelled images, our learned vanilla ResNet-50 achieves 81.2% top-1 accuracy on the ImageNet benchmark.