{
  "id": "2205.06160",
  "version": "v1",
  "published": "2022-05-12T15:34:37.000Z",
  "updated": "2022-05-12T15:34:37.000Z",
  "title": "Localized Vision-Language Matching for Open-vocabulary Object Detection",
  "authors": [
    "Maria A. Bravo",
    "Sudhanshu Mittal",
    "Thomas Brox"
  ],
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "In this work, we propose an open-world object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a location-guided image-caption matching technique to learn class labels for both novel and known classes in a weakly-supervised manner and second specializes the model for the object detection task using known class annotations. We show that a simple language model fits better than a large contextualized language model for detecting novel objects. Moreover, we introduce a consistency-regularization technique to better exploit image-caption pair information. Our method compares favorably to existing open-world detection approaches while being data-efficient.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2022-05-12T15:34:37.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "open-vocabulary object detection",
      "localized vision-language matching",
      "better exploit image-caption pair information",
      "simple language model fits better",
      "detect novel object classes"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}