PottsSAGNet: a Potts model-based segmentation network with self-attention and Gaussian regularization
From MaRDI portal
Cites work
- _1DecNet+: a new architecture framework by _1 decomposition and iteration unfolding for sparse feature segmentation
- A Color Elastica Model for Vector-Valued Image Regularization
- A fast operator-splitting method for Beltrami color image denoising
- A finite element/operator-splitting method for the numerical solution of the two dimensional elliptic Monge-Ampère equation
- A first-order primal-dual algorithm for convex problems with applications to imaging
- A New Operator Splitting Method for the Euler Elastica Model for Image Smoothing
- A non-local anisotropic model for phase transitions: asymptotic behaviour of rescaled energies
- A parallel splitting-up method for partial differential equations and its applications to Navier-Stokes equations
- A Penalization-Regularization-Operator Splitting Method for Eikonal Based Traveltime Tomography
- A proposal on machine learning via dynamical systems
- Active contours without edges
- Algorithms for Finding Global Minimizers of Image Segmentation and Denoising Models
- An efficient maximum bound principle preserving p-adaptive operator-splitting method for three-dimensional phase field shape transformation model
- An Operator-Splitting Method for the Gaussian Curvature Regularization Model with Applications to Surface Smoothing and Imaging
- Augmented Lagrangian method for an Euler's elastica based segmentation model that promotes convex contours
- Connections between Operator-Splitting Methods and Deep Neural Networks with Applications in Image Segmentation
- Convexity Shape Prior for Level Set-Based Image Segmentation Method
- Curvature Regularized Surface Reconstruction from Point Clouds
- Deep convolutional neural networks with spatial regularization, volume and star-shape priors for image segmentation
- Diffusion-generated motion by mean curvature for filaments
- Double-well net for image segmentation
- Efficient and convergent preconditioned ADMM for the Potts models
- Fast operator splitting methods for obstacle problems
- Fields of experts
- Geodesic active contours
- scientific article; zbMATH DE number 996056 (Why is no real title available?)
- scientific article; zbMATH DE number 3076589 (Why is no real title available?)
- On the numerical solution of nonlinear eigenvalue problems for the Monge-Ampère operator
- Operator splitting
- Operator splitting algorithms for free surface flows: application to extrusion processes
- Optimal approximations by piecewise smooth functions and associated variational problems
- PottsMGNet: a mathematical explanation of encoder-decoder based neural networks
- Some Facts About Operator-Splitting and Alternating Direction Methods
This page was built for publication: PottsSAGNet: a Potts model-based segmentation network with self-attention and Gaussian regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7346718)
