Riesz feature representation: scale equivariant scattering network for classification tasks

DOI10.1137/23M1584836MaRDI QIDQ6587644zbMATH OpenFDO

Authors Tin Barisin, Jesús Angulo, Katja Schladitz, Claudia Redenbach

Publication date 14 August 2024

Published in SIAM Journal on Imaging Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/23M1584836

zbMATH Keywords

Riesz transformscale equivariancescattering networkstexture classification

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Recommendations

• Riesz networks: scale-invariant neural networks in a single forward pass
• The Scattering Transform
• Scale-covariant and scale-invariant Gaussian derivative networks
• Scale-covariant and scale-invariant Gaussian derivative networks
• On generalizations of the nonwindowed scattering transform

Cites work

• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• Computer Vision - ECCV 2004
• Group invariant scattering
• scientific article; zbMATH DE number 1794201 (Why is no real title available?)
• Image matching using generalized scale-space interest points
• Linearized Riesz transform and quasi-monogenic shearlets
• Monogenic wavelet scattering network for texture image classification
• Multiresolution Monogenic Signal Analysis Using the Riesz–Laplace Wavelet Transform
• On the choice of band-pass quadrature filters
• Phase recovery, MaxCut and complex semidefinite programming
• Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
• Riesz networks: scale-invariant neural networks in a single forward pass
• Rock classification with features based on higher order Riesz transform
• Scale-covariant and scale-invariant Gaussian derivative networks
• Scale-invariant scale-channel networks: deep networks that generalise to previously unseen scales
• Scikit-learn: machine learning in Python
• Steerable Wavelet Frames Based on the Riesz Transform
• Structure detection with second order Riesz transforms
• The monogenic scale-space: a unifying approach to phase-based image processing in scale-space
• The monogenic signal
• The Monogenic Wavelet Transform
• Wavelet Steerability and the Higher-Order Riesz Transform

Cited in

(5)

• Monogenic wavelet scattering network for texture image classification
• Riesz networks: scale-invariant neural networks in a single forward pass
• Unified theory for joint covariance properties under geometric image transformations for spatio-temporal receptive fields according to the generalized Gaussian derivative model for visual receptive fields
• Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations
• Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields

This page was built for publication: Riesz feature representation: scale equivariant scattering network for classification tasks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6587644)