Double-Well Net for Image Segmentation
Multiscale Modeling & Simulation · 31.12.2024 · 22 (4) · 1449-1477
DOI: 10.1137/24m1632103 ↗Kurz gefasst
Fachartikel in der Zeitschrift Multiscale Modeling & Simulation, online erschienen am 05.11.2024. Verfasst von Hao Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 94 Literaturangaben. Gefördert von: Hong Kong Information Technology Federation, NORCE, Hong Kong Baptist University.
Abstract (Originalsprache)
In this study, our goal is to integrate classical mathematical models with deep neural networks by introducing two novel deep neural network models for image segmentation known as Double-well Nets. Drawing inspirations from the Potts model, our models leverage neural networks to represent a region force functional. We extend the well-known MBO (Merriman–Bence–Osher) scheme to solve the Potts model. The widely recognized Potts model is approximated using a double-well potential and then solved by an operator-splitting method, which turns out to be an extension of the well-known MBO scheme. Subsequently, we replace the region force functional in the Potts model with a UNet-type network, which is data-driven and is designed to capture multiscale features of images, and also introduce control variables to enhance effectiveness. The resulting algorithm is a neural network activated by a function that minimizes the double-well potential. What sets our proposed Double-well Nets apart from many existing deep learning methods for image segmentation is their strong mathematical foundation. They are derived from the network approximation theory and employ the MBO scheme to approximately solve the Potts model. By incorporating mathematical principles, Double-well Nets bridge the MBO scheme and neural networks, and offer an alternative perspective for designing networks with mathematical backgrounds. Through comprehensive experiments, we demonstrate the performance of Double-well Nets, showcasing their superior accuracy and robustness compared to state-of-the-art neural networks. Overall, our work represents a valuable contribution to the field of image segmentation by combining the strengths of classical variational models and deep neural networks. The Double-well Nets introduce an innovative approach that leverages mathematical foundations to enhance segmentation performance.
Förderung
- Hong Kong Information Technology Federation
- NORCE
- Hong Kong Baptist University
- National Natural Science Foundation of China
- Research Grants Council, University Grants Committee
Zitieren
APA
Liu, H., Liu, J., Chan, R. H., & Tai, X. (2024). Double-Well Net for Image Segmentation. Multiscale Modeling & Simulation, 22(4), 1449-1477. https://doi.org/10.1137/24m1632103
Vancouver
Liu H, Liu J, Chan RH, Tai X. Double-Well Net for Image Segmentation. Multiscale Modeling & Simulation. 2024;22(4):1449-1477. doi:10.1137/24m1632103
BibTeX
@article{Liu2024,
author = {Liu, Hao and Liu, Jun and Chan, Raymond H. and Tai, Xue-Cheng},
title = {Double-Well Net for Image Segmentation},
journal = {Multiscale Modeling & Simulation},
year = {2024},
volume = {22},
number = {4},
pages = {1449--1477},
doi = {10.1137/24m1632103}
}
EUVIMED