{
  "id": "2206.03012",
  "version": "v1",
  "published": "2022-06-07T05:03:05.000Z",
  "updated": "2022-06-07T05:03:05.000Z",
  "title": "TriBYOL: Triplet BYOL for Self-Supervised Representation Learning",
  "authors": [
    "Guang Li",
    "Ren Togo",
    "Takahiro Ogawa",
    "Miki Haseyama"
  ],
  "comment": "Published as a conference paper at ICASSP 2022",
  "doi": "10.1109/ICASSP43922.2022.9746967",
  "categories": [
    "cs.CV",
    "cs.AI"
  ],
  "abstract": "This paper proposes a novel self-supervised learning method for learning better representations with small batch sizes. Many self-supervised learning methods based on certain forms of the siamese network have emerged and received significant attention. However, these methods need to use large batch sizes to learn good representations and require heavy computational resources. We present a new triplet network combined with a triple-view loss to improve the performance of self-supervised representation learning with small batch sizes. Experimental results show that our method can drastically outperform state-of-the-art self-supervised learning methods on several datasets in small-batch cases. Our method provides a feasible solution for self-supervised learning with real-world high-resolution images that uses small batch sizes.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-06-07T05:03:05.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "self-supervised representation learning",
      "small batch sizes",
      "triplet byol",
      "state-of-the-art self-supervised learning methods",
      "outperform state-of-the-art self-supervised learning"
    ],
    "tags": [
      "conference paper",
      "journal article"
    ],
    "publication": {
      "publisher": "IEEE"
    },
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}