{
  "id": "1905.00546",
  "version": "v1",
  "published": "2019-05-02T02:08:18.000Z",
  "updated": "2019-05-02T02:08:18.000Z",
  "title": "Billion-scale semi-supervised learning for image classification",
  "authors": [
    "I. Zeki Yalniz",
    "Hervé Jégou",
    "Kan Chen",
    "Manohar Paluri",
    "Dhruv Mahajan"
  ],
  "categories": [
    "cs.CV"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-05-02T02:08:18.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "image classification",
      "billion-scale semi-supervised learning",
      "approach brings important gains",
      "produce high-accuracy models",
      "large convolutional networks"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}