{
  "id": "2003.04390",
  "version": "v1",
  "published": "2020-03-09T20:06:36.000Z",
  "updated": "2020-03-09T20:06:36.000Z",
  "title": "A New Meta-Baseline for Few-Shot Learning",
  "authors": [
    "Yinbo Chen",
    "Xiaolong Wang",
    "Zhuang Liu",
    "Huijuan Xu",
    "Trevor Darrell"
  ],
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "Meta-learning has become a popular framework for few-shot learning in recent years, with the goal of learning a model from collections of few-shot classification tasks. While more and more novel meta-learning models are being proposed, our research has uncovered simple baselines that have been overlooked. We present a Meta-Baseline method, by pre-training a classifier on all base classes and meta-learning on a nearest-centroid based few-shot classification algorithm, it outperforms recent state-of-the-art methods by a large margin. Why does this simple method work so well? In the meta-learning stage, we observe that a model generalizing better on unseen tasks from base classes can have a decreasing performance on tasks from novel classes, indicating a potential objective discrepancy. We find both pre-training and inheriting a good few-shot classification metric from the pre-trained classifier are important for Meta-Baseline, which potentially helps the model better utilize the pre-trained representations with stronger transferability. Furthermore, we investigate when we need meta-learning in this Meta-Baseline. Our work sets up a new solid benchmark for this field and sheds light on further understanding the phenomenons in the meta-learning framework for few-shot learning.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-03-09T20:06:36.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "few-shot learning",
      "meta-learning",
      "base classes",
      "few-shot classification metric",
      "simple method work"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}