{
  "id": "2410.13486",
  "version": "v1",
  "published": "2024-10-17T12:31:37.000Z",
  "updated": "2024-10-17T12:31:37.000Z",
  "title": "SemSim: Revisiting Weak-to-Strong Consistency from a Semantic Similarity Perspective for Semi-supervised Medical Image Segmentation",
  "authors": [
    "Shiao Xie",
    "Hongyi Wang",
    "Ziwei Niu",
    "Hao Sun",
    "Shuyi Ouyang",
    "Yen-Wei Chen",
    "Lanfen Lin"
  ],
  "categories": [
    "cs.CV"
  ],
  "abstract": "Semi-supervised learning (SSL) for medical image segmentation is a challenging yet highly practical task, which reduces reliance on large-scale labeled dataset by leveraging unlabeled samples. Among SSL techniques, the weak-to-strong consistency framework, popularized by FixMatch, has emerged as a state-of-the-art method in classification tasks. Notably, such a simple pipeline has also shown competitive performance in medical image segmentation. However, two key limitations still persist, impeding its efficient adaptation: (1) the neglect of contextual dependencies results in inconsistent predictions for similar semantic features, leading to incomplete object segmentation; (2) the lack of exploitation of semantic similarity between labeled and unlabeled data induces considerable class-distribution discrepancy. To address these limitations, we propose a novel semi-supervised framework based on FixMatch, named SemSim, powered by two appealing designs from semantic similarity perspective: (1) rectifying pixel-wise prediction by reasoning about the intra-image pair-wise affinity map, thus integrating contextual dependencies explicitly into the final prediction; (2) bridging labeled and unlabeled data via a feature querying mechanism for compact class representation learning, which fully considers cross-image anatomical similarities. As the reliable semantic similarity extraction depends on robust features, we further introduce an effective spatial-aware fusion module (SFM) to explore distinctive information from multiple scales. Extensive experiments show that SemSim yields consistent improvements over the state-of-the-art methods across three public segmentation benchmarks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-10-17T12:31:37.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "semi-supervised medical image segmentation",
      "semantic similarity perspective",
      "revisiting weak-to-strong consistency",
      "data induces considerable class-distribution",
      "induces considerable class-distribution discrepancy"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}