{
  "id": "2307.15710",
  "version": "v1",
  "published": "2023-07-28T17:59:03.000Z",
  "updated": "2023-07-28T17:59:03.000Z",
  "title": "Semi-Supervised Object Detection in the Open World",
  "authors": [
    "Garvita Allabadi",
    "Ana Lucic",
    "Peter Pao-Huang",
    "Yu-Xiong Wang",
    "Vikram Adve"
  ],
  "categories": [
    "cs.CV",
    "cs.LG"
  ],
  "abstract": "Existing approaches for semi-supervised object detection assume a fixed set of classes present in training and unlabeled datasets, i.e., in-distribution (ID) data. The performance of these techniques significantly degrades when these techniques are deployed in the open-world, due to the fact that the unlabeled and test data may contain objects that were not seen during training, i.e., out-of-distribution (OOD) data. The two key questions that we explore in this paper are: can we detect these OOD samples and if so, can we learn from them? With these considerations in mind, we propose the Open World Semi-supervised Detection framework (OWSSD) that effectively detects OOD data along with a semi-supervised learning pipeline that learns from both ID and OOD data. We introduce an ensemble based OOD detector consisting of lightweight auto-encoder networks trained only on ID data. Through extensive evalulation, we demonstrate that our method performs competitively against state-of-the-art OOD detection algorithms and also significantly boosts the semi-supervised learning performance in open-world scenarios.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-07-28T17:59:03.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semi-supervised object detection",
      "open world semi-supervised detection framework",
      "state-of-the-art ood detection algorithms",
      "effectively detects ood data",
      "object detection assume"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}