{
  "id": "2207.10150",
  "version": "v1",
  "published": "2022-07-20T19:07:46.000Z",
  "updated": "2022-07-20T19:07:46.000Z",
  "title": "Tackling Long-Tailed Category Distribution Under Domain Shifts",
  "authors": [
    "Xiao Gu",
    "Yao Guo",
    "Zeju Li",
    "Jianing Qiu",
    "Qi Dou",
    "Yuxuan Liu",
    "Benny Lo",
    "Guang-Zhong Yang"
  ],
  "comment": "accepted to ECCV 2022",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Machine learning models fail to perform well on real-world applications when 1) the category distribution P(Y) of the training dataset suffers from long-tailed distribution and 2) the test data is drawn from different conditional distributions P(X|Y). Existing approaches cannot handle the scenario where both issues exist, which however is common for real-world applications. In this study, we took a step forward and looked into the problem of long-tailed classification under domain shifts. We designed three novel core functional blocks including Distribution Calibrated Classification Loss, Visual-Semantic Mapping and Semantic-Similarity Guided Augmentation. Furthermore, we adopted a meta-learning framework which integrates these three blocks to improve domain generalization on unseen target domains. Two new datasets were proposed for this problem, named AWA2-LTS and ImageNet-LTS. We evaluated our method on the two datasets and extensive experimental results demonstrate that our proposed method can achieve superior performance over state-of-the-art long-tailed/domain generalization approaches and the combinations. Source codes and datasets can be found at our project page https://xiaogu.site/LTDS.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-07-20T19:07:46.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "tackling long-tailed category distribution",
      "domain shifts",
      "state-of-the-art long-tailed/domain generalization approaches",
      "novel core functional blocks",
      "real-world applications"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}