用频谱方法提升小数据下医学图像的高效分块，性能更好参数更少。
Spectral Vision Transformer for Efficient Tokenization with Limited Data
- 基于频谱基的分块方式，具备空间不变性和最佳信噪比。
- 相比传统方法，参数更少但表现持平或更优，复杂度更低。
- 适合医疗图像等小样本场景，代码已开源供复用。
我们提出一种新型频谱视觉变换器架构，用于在小数据条件下实现高效的图像分块，特别针对医学影像任务。所选基函数带来便捷的理论性质，包括空间不变性与最优信噪比。相比空间域视觉变换器，频谱投影显著降低计算复杂度。在模拟数据、公开数据及临床数据上的实验表明，该模型在参数量更少的情况下，性能与多种主流模型（包括紧凑型和标准型视觉变换器、带注意力的卷积神经网络、移位窗口变换器、多层感知机及逻辑回归）相当或更优。代码已发布于 github.com/agr78/spectralViT。
原文摘要 · Abstract (English)
We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline convenient theoretical properties arising from the choice of basis including spatial invariance and optimal signal-to-noise ratio. We show reduced complexity arising from the spectral projection compared to spatial vision transformers. We show equitable or superior performance with a reduced number of parameters as compared to a variety of models including compact and standard vision transformers, convolutional neural networks with attention, shifted window transformers, multi-layer perceptrons, and logistic regression. We include simulated, public, and clinical data in our analysis and release our code at: \verb+github.com/agr78/spectralViT+.
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。