{
  "id": "2011.14015",
  "version": "v1",
  "published": "2020-11-27T22:06:52.000Z",
  "updated": "2020-11-27T22:06:52.000Z",
  "title": "Active Learning in CNNs via Expected Improvement Maximization",
  "authors": [
    "Udai G. Nagpal",
    "David A Knowles"
  ],
  "categories": [
    "cs.LG",
    "cs.AI",
    "cs.CV"
  ],
  "abstract": "Deep learning models such as Convolutional Neural Networks (CNNs) have demonstrated high levels of effectiveness in a variety of domains, including computer vision and more recently, computational biology. However, training effective models often requires assembling and/or labeling large datasets, which may be prohibitively time-consuming or costly. Pool-based active learning techniques have the potential to mitigate these issues, leveraging models trained on limited data to selectively query unlabeled data points from a pool in an attempt to expedite the learning process. Here we present \"Dropout-based Expected IMprOvementS\" (DEIMOS), a flexible and computationally-efficient approach to active learning that queries points that are expected to maximize the model's improvement across a representative sample of points. The proposed framework enables us to maintain a prediction covariance matrix capturing model uncertainty, and to dynamically update this matrix in order to generate diverse batches of points in the batch-mode setting. Our active learning results demonstrate that DEIMOS outperforms several existing baselines across multiple regression and classification tasks taken from computer vision and genomics.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-11-27T22:06:52.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "I.2.6",
      "I.5.4",
      "I.4.9"
    ],
    "keywords": [
      "active learning",
      "expected improvement maximization",
      "query unlabeled data points",
      "matrix capturing model uncertainty",
      "prediction covariance matrix capturing model"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}