Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade

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.

29 pages, 16 figures, 3 tables. arXiv admin note: substantial text overlap with arXiv:1903.00289

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
• A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
• Mathematics of Deep Learning
• Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields
• Estimating Information Flow in Deep Neural Networks
• A Differential Model of the Complex Cell
• Rotational 3D Texture Classification Using Group Equivariant CNNs
• Provably scale-covariant networks from oriented quasi quadrature measures in cascade

Cited by in corpus (9)

• Scale-covariant and scale-invariant Gaussian derivative networks
• Understanding when spatial transformer networks do not support invariance, and what to do about it
• Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales
• Covariance properties under natural image transformations for the generalized Gaussian derivative model for visual receptive fields
• 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
• 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?
• Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations
• Approximation properties relative to continuous scale space for hybrid discretizations of Gaussian derivative operators