{
  "id": "2404.00380",
  "version": "v1",
  "published": "2024-03-30T14:35:31.000Z",
  "updated": "2024-03-30T14:35:31.000Z",
  "title": "DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation",
  "authors": [
    "Sanghyun Jo",
    "Fei Pan",
    "In-Jae Yu",
    "Kyungsu Kim"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything. However, WSS faces challenges related to minor classes since those are overlooked in images with adjacent multiple classes, a limitation originating from the overfitting of traditional expansion methods like Random Walk. We first address this by employing unsupervised and weakly-supervised feature maps instead of conventional methodologies, allowing for hierarchical mask enhancement. This method distinctly categorizes higher-level classes and subsequently separates their associated lower-level classes, ensuring all classes are correctly restored in the mask without losing minor ones. Our approach, validated through extensive experimentation, significantly improves WSS across five benchmarks (VOC: 79.8\\%, COCO: 53.9\\%, Context: 49.0\\%, ADE: 32.9\\%, Stuff: 37.4\\%), reducing the gap with fully supervised methods by over 84\\% on the VOC validation set. Code is available at https://github.com/shjo-april/DHR.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-03-30T14:35:31.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "weakly-supervised semantic segmentation",
      "dual features-driven hierarchical rebalancing",
      "intra-class regions",
      "method distinctly categorizes higher-level classes",
      "wss faces challenges"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}