Billion-scale semi-supervised learning for image classification

Code

• github.com/salesforce/ensemble-of-averages
  pytorch★ 31
• github.com/tiskw/patchcore-ad
  pytorch★ 27
• github.com/leaderj1001/Billion-scale-semi-supervised-learning
  pytorch★ 0
• github.com/facebookresearch/semi-supervised-ImageNet1K-models
  pytorch★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions