DDU-Net: A Domain Decomposition-Based CNN for High-Resolution Image Segmentation on Multiple GPUs

TL;DR

This paper introduces DDU-Net, a novel CNN architecture that employs domain decomposition and inter-patch communication to efficiently segment ultra-high-resolution images across multiple GPUs, maintaining spatial context and improving accuracy.

Contribution

The paper presents a new domain decomposition-based U-Net architecture with inter-patch communication, enabling high-resolution image segmentation on multiple GPUs without losing spatial information.

Findings

Achieves 2-3% higher IoU with inter-patch communication.

Performs comparably to full-image U-Net on benchmark datasets.

Effectively segments ultra-high-resolution images while preserving spatial context.

Abstract

The segmentation of ultra-high resolution images poses challenges such as loss of spatial information or computational inefficiency. In this work, a novel approach that combines encoder-decoder architectures with domain decomposition strategies to address these challenges is proposed. Specifically, a domain decomposition-based U-Net (DDU-Net) architecture is introduced, which partitions input images into non-overlapping patches that can be processed independently on separate devices. A communication network is added to facilitate inter-patch information exchange to enhance the understanding of spatial context. Experimental validation is performed on a synthetic dataset that is designed to measure the effectiveness of the communication network. Then, the performance is tested on the DeepGlobe land cover classification dataset as a real-world benchmark data set. The results demonstrate that the approach, which includes inter-patch communication for images divided into $16\times16$ non-overlapping subimages, achieves a $2-3\,\%$ higher intersection over union (IoU) score compared to the same network without inter-patch communication. The performance of the network which includes communication is equivalent to that of a baseline U-Net trained on the full image, showing that our model provides an effective solution for segmenting ultra-high-resolution images while preserving spatial context. The code is available at https://github.com/corne00/DDU-Net.