解决医学图像分割中特征同质与语义过平滑问题
SAM-DCE: Addressing Token Uniformity and Semantic Over-Smoothing in Medical Segmentation
- 引入SAM-DCE模型，平衡局部差异与全局语义
- 提升不同类别间可分性，减少特征冗余
- 适合需要高精度医学图像分割的研究者
分割一切模型（SAM）在自然图像上表现出色的零样本分割能力，但在医学影像中因领域偏移、解剖结构变异以及依赖人工提示而面临挑战。近期无需提示的改进方法虽减轻了专家干预需求，但仍存在鲁棒性不足、适应性差的问题，常忽略语义过平滑和标记同质化。本文提出SAM-DCE，在保持局部判别力与全局语义一致性的基础上，缓解标记同质化，增强类别间可分性，并通过细粒度、一致的表示丰富掩码解码。在多个医学基准上的大量实验验证了其有效性。
原文摘要 · Abstract (English)
The Segment Anything Model (SAM) demonstrates impressive zero-shot segmentation ability on natural images but encounters difficulties in medical imaging due to domain shifts, anatomical variability, and its reliance on user-provided prompts. Recent prompt-free adaptations alleviate the need for expert intervention, yet still suffer from limited robustness and adaptability, often overlooking the issues of semantic over-smoothing and token uniformity. We propose SAM-DCE, which balances local discrimination and global semantics while mitigating token uniformity, enhancing inter-class separability, and enriching mask decoding with fine-grained, consistent representations. Extensive experiments on diverse medical benchmarks validate its effectiveness.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。