{
  "id": "2112.04564",
  "version": "v2",
  "published": "2021-12-08T20:13:13.000Z",
  "updated": "2022-05-13T20:43:44.000Z",
  "title": "CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning",
  "authors": [
    "Yue Fan",
    "Dengxin Dai",
    "Bernt Schiele"
  ],
  "comment": "Published at CVPR 2022 as a conference paper. Code at https://github.com/YUE-FAN/CoSSL",
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "In this paper, we propose a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL. To handle the data imbalance, we devise Tail-class Feature Enhancement (TFE) for classifier learning. Furthermore, the current evaluation protocol for imbalanced SSL focuses only on balanced test sets, which has limited practicality in real-world scenarios. Therefore, we further conduct a comprehensive evaluation under various shifted test distributions. In experiments, we show that our approach outperforms other methods over a large range of shifted distributions, achieving state-of-the-art performance on benchmark datasets ranging from CIFAR-10, CIFAR-100, ImageNet, to Food-101. Our code will be made publicly available.",
  "revisions": [
    {
      "version": "v2",
      "updated": "2022-05-13T20:43:44.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "imbalanced semi-supervised learning",
      "representation",
      "devise tail-class feature enhancement",
      "current evaluation protocol",
      "co-learning"
    ],
    "tags": [
      "conference paper",
      "github project"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}