DeepAI AI Chat
Log In Sign Up

Equivariant Wavelets: Fast Rotation and Translation Invariant Wavelet Scattering Transforms

by   Andrew K. Saydjari, et al.

Wavelet scattering networks, which are convolutional neural networks (CNNs) with fixed filters and weights, are promising tools for image analysis. Imposing symmetry on image statistics can improve human interpretability, aid in generalization, and provide dimension reduction. In this work, we introduce a fast-to-compute, translationally invariant and rotationally equivariant wavelet scattering network (EqWS) and filter bank of wavelets (triglets). We demonstrate the interpretability and quantify the invariance/equivariance of the coefficients, briefly commenting on difficulties with implementing scale equivariance. On MNIST, we show that training on a rotationally invariant reduction of the coefficients maintains rotational invariance when generalized to test data and visualize residual symmetry breaking terms. Rotation equivariance is leveraged to estimate the rotation angle of digits and reconstruct the full rotation dependence of each coefficient from a single angle. We benchmark EqWS with linear classifiers on EMNIST and CIFAR-10/100, introducing a new second-order, cross-color channel coupling for the color images. We conclude by comparing the performance of an isotropic reduction of the scattering coefficients and RWST, a previous coefficient reduction, on an isotropic classification of magnetohydrodynamic simulations with astrophysical relevance.


page 1

page 3

page 5

page 7

page 14

page 16

page 18


Group Invariant Scattering

This paper constructs translation invariant operators on L2(R^d), which ...

Performance evaluation of wavelet scattering network in image texture classification in various color spaces

Texture plays an important role in many image analysis applications. In ...

Rotation invariant CNN using scattering transform for image classification

Deep convolutional neural networks accuracy is heavily impacted by rotat...

Underwater object classification using scattering transform of sonar signals

In this paper, we apply the scattering transform (ST), a nonlinear map b...

Deep Learning in the Wavelet Domain

This paper examines the possibility of, and the possible advantages to l...

Sparse Multi-Family Deep Scattering Network

In this work, we propose the Sparse Multi-Family Deep Scattering Network...

Unsupervised Deep Haar Scattering on Graphs

The classification of high-dimensional data defined on graphs is particu...