{
  "id": "2208.13946",
  "version": "v1",
  "published": "2022-08-30T01:27:48.000Z",
  "updated": "2022-08-30T01:27:48.000Z",
  "title": "PercentMatch: Percentile-based Dynamic Thresholding for Multi-Label Semi-Supervised Classification",
  "authors": [
    "Junxiang Huang",
    "Alexander Huang",
    "Beatriz C. Guerra",
    "Yen-Yun Yu"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "While much of recent study in semi-supervised learning (SSL) has achieved strong performance on single-label classification problems, an equally important yet underexplored problem is how to leverage the advantage of unlabeled data in multi-label classification tasks. To extend the success of SSL to multi-label classification, we first analyze with illustrative examples to get some intuition about the extra challenges exist in multi-label classification. Based on the analysis, we then propose PercentMatch, a percentile-based threshold adjusting scheme, to dynamically alter the score thresholds of positive and negative pseudo-labels for each class during the training, as well as dynamic unlabeled loss weights that further reduces noise from early-stage unlabeled predictions. Without loss of simplicity, we achieve strong performance on Pascal VOC2007 and MS-COCO datasets when compared to recent SSL methods.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-08-30T01:27:48.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "multi-label semi-supervised classification",
      "percentile-based dynamic thresholding",
      "percentmatch",
      "achieve strong performance",
      "single-label classification problems"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}