Scale-covariant and scale-invariant Gaussian derivative networks

DOI10.1007/s10851-021-01057-9OpenAlexW3109158212MaRDI QIDQ5918660

Tony Lindeberg

Publication date: 20 April 2022

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.14759

zbMATH Keywords

scale invariancescale spacescale covariancedeep learningGaussian derivativescale selectionscale generalisation

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Related Items (1)

Scale-invariant scale-channel networks: deep networks that generalise to previously unseen scales

Uses Software

• MNIST
• DeepLab
• SIFT
• OverFeat
• PyTorch
• Adam
• ScatNet
• SURF
• ESPNet
• PointConv

Cites Work

• Unnamed Item
• Linear scale-space has first been proposed in Japan
• A computational theory of visual receptive fields
• The structure of images
• Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations
• Representation of local geometry in the visual system
• Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space
• Deep neural networks motivated by partial differential equations
• On the axioms of scale space theory
• Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
• Image matching using generalized scale-space interest points
• The monogenic scale-space: a unifying approach to phase-based image processing in scale-space
• Uniqueness of the Gaussian Kernel for Scale-Space Filtering
• Dense Scale Selection Over Space, Time, and Space-Time
• Scale-covariant and scale-invariant Gaussian derivative networks

This page was built for publication: Scale-covariant and scale-invariant Gaussian derivative networks