A Unified Framework for U-Net Design and Analysis

Christopher Williams, Fabian Falck, George Deligiannidis, Christopher C. Holmes, Arnaud Doucet, Saifuddin Syed

Keywords: U-Net, ResNet, Multi-ResNet, Generalised U-Net, Wavelets, Diffusion models, Generative modelling, PDE Modelling, Image Segmentation

TL;DR: We present a framework for designing and analysing general U-Nets.

Abstract: U-Nets are a go-to neural architecture across numerous tasks for continuous signals on a square such as images and Partial Differential Equations (PDE), however their design and architecture is understudied. In this paper, we provide a framework for designing and analysing general U-Net architectures. We present theoretical results which characterise the role of the encoder and decoder in a U-Net, their high-resolution scaling limits and their conjugacy to ResNets via preconditioning. We propose Multi-ResNets, U-Nets with a simplified, wavelet-based encoder without learnable parameters. Further, we show how to design novel U-Net architectures which encode function constraints, natural bases, or the geometry of the data. In diffusion models, our framework enables us to identify that high-frequency information is dominated by noise exponentially faster, and show how U-Nets with average pooling exploit this. In our experiments, we demonstrate how Multi-ResNets achieve competitive and often superior performance compared to classical U-Nets in image segmentation, PDE surrogate modelling, and generative modelling with diffusion models. Our U-Net framework paves the way to study the theoretical properties of U-Nets and design natural, scalable neural architectures for a multitude of problems beyond the square.

Submission Number: 11738