Some open questions on morphological operators and representations in the deep learning era. A personal vision

DOI10.1007/978-3-030-76657-3_1zbMath1484.68267arXiv2105.01339OpenAlexW3163701712MaRDI QIDQ2061783

Publication date: 21 December 2021

Full work available at URL: https://arxiv.org/abs/2105.01339

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Machine vision and scene understanding (68T45)

Related Items (1)

Toward a sparsity theory on weighted lattices

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Grey-level hit-or-miss transforms. I: Unified theory
Stability of persistence diagrams
A remark on regularization in Hilbert spaces
Max-min representation of piecewise linear functions
Adjunctions in pyramids, curve evolution and scale-spaces
Deep neural networks motivated by partial differential equations
A gentle introduction to deep learning for graphs
Hierarchical Laplacian and its spectrum in ultrametric image processing
Max-plus operators applied to filter selection and model pruning in neural networks
Encyclopedia of Continuum Mechanics
PDE-based Morphology for Matrix Fields: Numerical Solution Schemes
A representation theory for morphological image and signal processing
Minimal Representations for Translation-Invariant Set Mappings by Mathematical Morphology
A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
General Constructive Representations for Continuous Piecewise-Linear Functions
Playing with Kruskal: Algorithms for Morphological Trees in Edge-Weighted Graphs
Stochastic Morphological Filtering and Bellman-Maslov Chains
A Learning Framework for Morphological Operators Using Counter–Harmonic Mean
ESTIMATES FOR SOLUTIONS TO DISCRETE CONVOLUTION EQUATIONS
Morphological Perceptrons: Geometry and Training Algorithms
Morphological Semigroups and Scale-Spaces on Ultrametric Spaces
A Unified Approach to PDE-Driven Morphology for Fields of Orthogonal and Generalized Doubly-Stochastic Matrices
Ultrametric fitting by gradient descent ^*
Boolean representations of manifolds and functions

This page was built for publication: Some open questions on morphological operators and representations in the deep learning era. A personal vision