HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation

TL;DR

HartleyMHA introduces a frequency domain self-attention model inspired by Fourier neural operators, achieving resolution robustness and efficiency in 3D image segmentation with significantly fewer parameters.

Contribution

The paper proposes HartleyMHA, a novel frequency domain self-attention mechanism based on FNO and Hartley transform, improving resolution robustness and parameter efficiency in 3D segmentation.

Findings

Outperforms other models in resolution robustness on BraTS'19 dataset.

Uses less than 1% of parameters compared to comparable models.

Achieves efficient high-order feature integration in 3D segmentation.

Abstract

With the introduction of Transformers, different attention-based models have been proposed for image segmentation with promising results. Although self-attention allows capturing of long-range dependencies, it suffers from a quadratic complexity in the image size especially in 3D. To avoid the out-of-memory error during training, input size reduction is usually required for 3D segmentation, but the accuracy can be suboptimal when the trained models are applied on the original image size. To address this limitation, inspired by the Fourier neural operator (FNO), we introduce the HartleyMHA model which is robust to training image resolution with efficient self-attention. FNO is a deep learning framework for learning mappings between functions in partial differential equations, which has the appealing properties of zero-shot super-resolution and global receptive field. We modify the FNO by using the Hartley transform with shared parameters to reduce the model size by orders of magnitude, and this allows us to further apply self-attention in the frequency domain for more expressive high-order feature combination with improved efficiency. When tested on the BraTS'19 dataset, it achieved superior robustness to training image resolution than other tested models with less than 1% of their model parameters.