用KAN改进Swin Transformer，让医学图像分割更高效准确
When Swin Transformer Meets KANs: An Improved Transformer Architecture for Medical Image Segmentation
- 将Kolmogorov-Arnold网络融入Swin编码器，提升表达能力
- 在4个数据集上达到顶尖性能，尤其在小样本下优势明显
- 适合追求高精度与低资源消耗的医疗影像研究者
医学图像分割对精准诊断和治疗规划至关重要，但受复杂解剖结构和标注数据有限的挑战。基于CNN的方法擅长局部特征提取，却难以建模长距离依赖；而Transformer虽能捕捉全局上下文，但数据需求高且计算成本大。本文提出UKAST——一种类似U-Net的架构，将基于有理函数的柯尔莫哥洛夫-阿诺德网络（KANs）嵌入Swin Transformer编码器。通过采用有理基函数与组有理KAN（GR-KANs），解决了传统样条KAN效率低的问题，构建出更具表达力且数据高效的框架，浮点运算量（FLOPs）更低，参数量仅轻微增加。UKAST在四个2D与3D医学图像分割基准上均达当前最优表现，显著超越各类CNN与Transformer基线，尤其在数据稀缺场景中表现优异，缓解了标准视觉Transformer的数据饥渴问题。代码已开源。
原文摘要 · Abstract (English)
Medical image segmentation is critical for accurate diagnostics and treatment planning, but remains challenging due to complex anatomical structures and limited annotated training data. CNN-based segmentation methods excel at local feature extraction, but struggle with modeling long-range dependencies. Transformers, on the other hand, capture global context more effectively, but are inherently data-hungry and computationally expensive. In this work, we introduce UKAST, a U-Net like architecture that integrates rational-function based Kolmogorov-Arnold Networks (KANs) into Swin Transformer encoders. By leveraging rational base functions and Group Rational KANs (GR-KANs) from the Kolmogorov-Arnold Transformer (KAT), our architecture addresses the inefficiencies of vanilla spline-based KANs, yielding a more expressive and data-efficient framework with reduced FLOPs and only a very small increase in parameter count compared to SwinUNETR. UKAST achieves state-of-the-art performance on four diverse 2D and 3D medical image segmentation benchmarks, consistently surpassing both CNN- and Transformer-based baselines. Notably, it attains superior accuracy in data-scarce settings, alleviating the data-hungry limitations of standard Vision Transformers. These results show the potential of KAN-enhanced Transformers to advance data-efficient medical image segmentation. Code is available at: https://github.com/nsapkota417/UKAST
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。