{
  "id": "1803.01529",
  "version": "v1",
  "published": "2018-03-05T07:30:58.000Z",
  "updated": "2018-03-05T07:30:58.000Z",
  "title": "LSTD: A Low-Shot Transfer Detector for Object Detection",
  "authors": [
    "Hao Chen",
    "Yali Wang",
    "Guoyou Wang",
    "Yu Qiao"
  ],
  "comment": "Accepted by AAAI2018",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Recent advances in object detection are mainly driven by deep learning with large-scale detection benchmarks. However, the fully-annotated training set is often limited for a target detection task, which may deteriorate the performance of deep detectors. To address this challenge, we propose a novel low-shot transfer detector (LSTD) in this paper, where we leverage rich source-domain knowledge to construct an effective target-domain detector with very few training examples. The main contributions are described as follows. First, we design a flexible deep architecture of LSTD to alleviate transfer difficulties in low-shot detection. This architecture can integrate the advantages of both SSD and Faster RCNN in a unified deep framework. Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images. Finally, we examine our LSTD on a number of challenging low-shot detection experiments, where LSTD outperforms other state-of-the-art approaches. The results demonstrate that LSTD is a preferable deep detector for low-shot scenarios.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-03-05T07:30:58.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "object detection",
      "low-shot detection",
      "deep detector",
      "leverage rich source-domain knowledge",
      "novel low-shot transfer detector"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}