{
  "id": "2305.14813",
  "version": "v1",
  "published": "2023-05-24T07:09:25.000Z",
  "updated": "2023-05-24T07:09:25.000Z",
  "title": "Semi-Supervised and Long-Tailed Object Detection with CascadeMatch",
  "authors": [
    "Yuhang Zang",
    "Kaiyang Zhou",
    "Chen Huang",
    "Chen Change Loy"
  ],
  "comment": "International Journal of Computer Vision (IJCV), 2023",
  "categories": [
    "cs.CV"
  ],
  "abstract": "This paper focuses on long-tailed object detection in the semi-supervised learning setting, which poses realistic challenges, but has rarely been studied in the literature. We propose a novel pseudo-labeling-based detector called CascadeMatch. Our detector features a cascade network architecture, which has multi-stage detection heads with progressive confidence thresholds. To avoid manually tuning the thresholds, we design a new adaptive pseudo-label mining mechanism to automatically identify suitable values from data. To mitigate confirmation bias, where a model is negatively reinforced by incorrect pseudo-labels produced by itself, each detection head is trained by the ensemble pseudo-labels of all detection heads. Experiments on two long-tailed datasets, i.e., LVIS and COCO-LT, demonstrate that CascadeMatch surpasses existing state-of-the-art semi-supervised approaches -- across a wide range of detection architectures -- in handling long-tailed object detection. For instance, CascadeMatch outperforms Unbiased Teacher by 1.9 AP Fix on LVIS when using a ResNet50-based Cascade R-CNN structure, and by 1.7 AP Fix when using Sparse R-CNN with a Transformer encoder. We also show that CascadeMatch can even handle the challenging sparsely annotated object detection problem.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2023-05-24T07:09:25.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "long-tailed object detection",
      "detection head",
      "existing state-of-the-art semi-supervised approaches",
      "ap fix",
      "sparsely annotated object detection problem"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}