Connections between Operator-Splitting Methods and Deep Neural Networks with Applications in Image Segmentation

DOI10.4208/aam.oa-2023-0027arXiv2307.09052OpenAlexW4388398069MaRDI QIDQ6151361

Raymond Honfu Chan, Unnamed Author, Xue-Cheng Tai

Publication date: 11 March 2024

Published in: Annals of Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2307.09052

zbMATH Keywords

operator splittingPotts modelimage segmentationdeep neural network

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Global minimization for continuous multiphase partitioning problems using a dual approach
• Augmented Lagrangian method for an Euler's elastica based segmentation model that promotes convex contours
• Geodesic active contours
• An efficient iterative thresholding method for image segmentation
• The gradient theory of phase transitions and the minimal interface criterion
• A first-order primal-dual algorithm for convex problems with applications to imaging
• A finite element/operator-splitting method for the numerical solution of the two dimensional elliptic Monge-Ampère equation
• Model reduction and neural networks for parametric PDEs
• Deep convolutional neural networks with spatial regularization, volume and star-shape priors for image segmentation
• An efficient maximum bound principle preserving p-adaptive operator-splitting method for three-dimensional phase field shape transformation model
• A fast operator-splitting method for Beltrami color image denoising
• Theory of deep convolutional neural networks: downsampling
• Error bounds for approximations with deep ReLU networks
• Universality of deep convolutional neural networks
• A three-stage approach for segmenting degraded color images: smoothing, lifting and thresholding (SLaT)
• Convex non-convex image segmentation
• Fast operator splitting methods for obstacle problems
• A Two-Stage Image Segmentation Method for Blurry Images with Poisson or Multiplicative Gamma Noise
• Optimal approximations by piecewise smooth functions and associated variational problems
• A Fast Relaxed Normal Two Split Method and an Effective Weighted TV Approach for Euler's Elastica Image Inpainting
• A Penalization-Regularization-Operator Splitting Method for Eikonal Based Traveltime Tomography
• A parallel splitting-up method for partial differential equations and its applications to Navier-Stokes equations
• Product formulas and numerical algorithms
• Universal approximation bounds for superpositions of a sigmoidal function
• Active contours without edges
• Efficient and Convergent Preconditioned ADMM for the Potts Models
• Error estimates for DeepONets: a deep learning framework in infinite dimensions
• An Operator-Splitting Method for the Gaussian Curvature Regularization Model with Applications to Surface Smoothing and Imaging
• Curvature Regularized Surface Reconstruction from Point Clouds
• Deep Network Approximation for Smooth Functions
• Some Facts About Operator-Splitting and Alternating Direction Methods
• Operator Splitting
• Operator Splitting Algorithms for Free Surface Flows: Application to Extrusion Processes
• On the Construction and Comparison of Difference Schemes
• On the numerical solution of nonlinear eigenvalue problems for the Monge-Ampère operator
• A Color Elastica Model for Vector-Valued Image Regularization
• Approximation by superpositions of a sigmoidal function
• Neural ODE Control for Classification, Approximation, and Transport
• Elastica Models for Color Image Regularization
• A New Operator Splitting Method for the Euler Elastica Model for Image Smoothing

This page was built for publication: Connections between Operator-Splitting Methods and Deep Neural Networks with Applications in Image Segmentation