{
  "id": "1909.11722",
  "version": "v1",
  "published": "2019-09-25T19:33:05.000Z",
  "updated": "2019-09-25T19:33:05.000Z",
  "title": "A Theoretical Analysis of the Number of Shots in Few-Shot Learning",
  "authors": [
    "Tianshi Cao",
    "Marc Law",
    "Sanja Fidler"
  ],
  "comment": "15 pages incl. appendix, 6 figures",
  "categories": [
    "cs.LG",
    "cs.AI",
    "stat.ML"
  ],
  "abstract": "Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks during meta-training to quickly adapt to new tasks during meta-testing. In this formulation, the number of shots exploited during meta-training has an impact on the recognition performance at meta-test time. Generally, the shot number used in meta-training should match the one used in meta-testing to obtain the best performance. We introduce a theoretical analysis of the impact of the shot number on Prototypical Networks, a state-of-the-art few-shot classification method. From our analysis, we propose a simple method that is robust to the choice of shot number used during meta-training, which is a crucial hyperparameter. The performance of our model trained for an arbitrary meta-training shot number shows great performance for different values of meta-testing shot numbers. We experimentally demonstrate our approach on different few-shot classification benchmarks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-09-25T19:33:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "theoretical analysis",
      "few-shot learning",
      "performance",
      "state-of-the-art few-shot classification method",
      "labeled examples"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 15,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}