{
  "id": "1810.12513",
  "version": "v1",
  "published": "2018-10-30T03:37:09.000Z",
  "updated": "2018-10-30T03:37:09.000Z",
  "title": "Weak-supervision for Deep Representation Learning under Class Imbalance",
  "authors": [
    "Shin Ando"
  ],
  "categories": [
    "cs.LG",
    "stat.ML"
  ],
  "abstract": "Class imbalance is a pervasive issue among classification models including deep learning, whose capacity to extract task-specific features is affected in imbalanced settings. However, the challenges of handling imbalance among a large number of classes, commonly addressed by deep learning, have not received a significant amount of attention in previous studies. In this paper, we propose an extension of the deep over-sampling framework, to exploit automatically-generated abstract-labels, i.e., a type of side-information used in weak-label learning, to enhance deep representation learning against class imbalance. We attempt to exploit the labels to guide the deep representation of instances towards different subspaces, to induce a soft-separation of inherent subtasks of the classification problem. Our empirical study shows that the proposed framework achieves a substantial improvement on image classification benchmarks with imbalanced among large and small numbers of classes.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-10-30T03:37:09.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "class imbalance",
      "weak-supervision",
      "image classification benchmarks",
      "extract task-specific features",
      "deep learning"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}