Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
From MaRDI portal
Publication:2303264
Abstract: This article presents a theory for constructing hierarchical networks in such a way that the networks are guaranteed to be provably scale covariant. We first present a general sufficiency argument for obtaining scale covariance, which holds for a wide class of networks defined from linear and non-linear differential expressions expressed in terms of scale-normalized scale-space derivatives. Then, we present a more detailed development of one example of such a network constructed from a combination of mathematically derived models of receptive fields and biologically inspired computations. Based on a functional model of complex cells in terms of an oriented quasi quadrature combination of first- and second-order directional Gaussian derivatives, we couple such primitive computations in cascade over combinatorial expansions over image orientations. Scale-space properties of the computational primitives are analysed and we give explicit proofs of how the resulting representation allows for scale and rotation covariance. A prototype application to texture analysis is developed and it is demonstrated that a simplified mean-reduced representation of the resulting QuasiQuadNet leads to promising experimental results on three texture datasets.
Recommendations
Cites work
- A computational theory of visual receptive fields
- A Differential Model of the Complex Cell
- A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
- BRINT: Binary Rotation Invariant and Noise Tolerant Texture Classification
- Dense scale selection over space, time, and space-time
- Generalized Gaussian scale-space axiomatics comprising linear scale-space, affine scale-space and spatio-temporal scale-space
- scientific article; zbMATH DE number 517283 (Why is no real title available?)
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- Image matching using generalized scale-space interest points
- Learning Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection
- Linear scale-space has first been proposed in Japan
- Median Robust Extended Local Binary Pattern for Texture Classification
- Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
- On the axioms of scale space theory
- PCANet: A Simple Deep Learning Baseline for Image Classification?
- Receptive field families
- Scaling Theorems for Zero Crossings
- The structure of images
- Time-causal and time-recursive spatio-temporal receptive fields
- Uniqueness of the Gaussian Kernel for Scale-Space Filtering
- Why does deep and cheap learning work so well?
Cited in
(11)- Scale-invariant scale-channel networks: deep networks that generalise to previously unseen scales
- Scale-invariant learning and convolutional networks
- Scale-covariant and scale-invariant Gaussian derivative networks
- Scale-covariant and scale-invariant Gaussian derivative networks
- Riesz feature representation: scale equivariant scattering network for classification tasks
- 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
- Orientation selectivity properties for the affine Gaussian derivative and the affine Gabor models for visual receptive fields
- Do the receptive fields in the primary visual cortex span a variability over the degree of elongation of the receptive fields?
- Hybrid Lie semi-group and cascade structures for the generalized Gaussian derivative model for visual receptive fields
Describes a project that uses
Uses Software
This page was built for publication: Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2303264)
