Challenges and opportunities in machine learning for geometry
R Magdalena-Benedicto, S Pérez-Díaz, A Costa-Roig - Mathematics, 2023 - mdpi.com
Over the past few decades, the mathematical community has accumulated a significant
amount of pure mathematical data, which has been analyzed through supervised, semi …
amount of pure mathematical data, which has been analyzed through supervised, semi …
Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges
Automating the current bridge visual inspection practices using drones and image
processing techniques is a prominent way to make these inspections more effective, robust …
processing techniques is a prominent way to make these inspections more effective, robust …
Functional properties of pde-based group equivariant convolutional neural networks
We build on the recently introduced PDE-G-CNN framework, which proposed the concept of
non-linear morphological convolutions that are motivated by solving HJB-PDEs on lifted …
non-linear morphological convolutions that are motivated by solving HJB-PDEs on lifted …
Geometric Generative Models based on Morphological Equivariant PDEs and GANs
Content and image generation consist in creating or generating data from noisy information
by extracting specific features such as texture, edges, and other thin image structures. We …
by extracting specific features such as texture, edges, and other thin image structures. We …
Connected Components on Lie Groups and Applications to Multi-Orientation Image Analysis
We develop and analyze a new algorithm to find the connected components of a compact
set I from a Lie group G endowed with a left-invariant Riemannian distance. For a given …
set I from a Lie group G endowed with a left-invariant Riemannian distance. For a given …
Current Symmetry Group Equivariant Convolution Frameworks for Representation Learning
R Basheer, D Mishra - arXiv preprint arXiv:2409.07327, 2024 - arxiv.org
Euclidean deep learning is often inadequate for addressing real-world signals where the
representation space is irregular and curved with complex topologies. Interpreting the …
representation space is irregular and curved with complex topologies. Interpreting the …
PDE-CNNs: Axiomatic Derivations and Applications
PDE-based Group Convolutional Neural Networks (PDE-G-CNNs) utilize solvers of
geometrically meaningful evolution PDEs as substitutes for the conventional components in …
geometrically meaningful evolution PDEs as substitutes for the conventional components in …
Optimal Transport on the Lie Group of Roto-translations
The roto-translation group SE2 has been of active interest in image analysis due to methods
that lift the image data to multi-orientation representations defined on this Lie group. This …
that lift the image data to multi-orientation representations defined on this Lie group. This …
[PDF][PDF] Axiomatic PDE-G-CNN on SE (2)
S Sakata - 2023 - bellaard.com
The field of machine learning is currently undergoing rapid development, with applications
in various areas, including image processing. In particular, Convolutional Neural Networks …
in various areas, including image processing. In particular, Convolutional Neural Networks …
Tensorial restoration neural network for digital textual image inpainting
Y Fan, J Tan, W Li, L Zou - Fourth International Conference on …, 2024 - spiedigitallibrary.org
A new neural network model called Tensorial Restoration Neural Network Model (TRNNM)
is proposed, which can repair the noise, blur, and information missing of digital textual …
is proposed, which can repair the noise, blur, and information missing of digital textual …