Parametric Scattering Networks

Abstract

The wavelet scattering transform creates geometric invariants and deformation stability from an initial structured signal.In multiple signal domains it has been shown to yield more discriminative representations compared to other non-learned representations, and to outperform learned representations in certain tasks, particularly on limited labeled data and highly structured signals. The wavelet filters used in the scattering transform are typically selected to create a tight frame via a parameterized mother wavelet. Focusing on Morlet wavelets, we propose to instead adapt the scales, orientations, and slants of the filters to produce problem-specific parametrizations of the scattering transform. We show that our learned versions of the scattering transform yield significant performance gains over the standard scattering transform in the small sample classification settings, and our empirical results suggest that tight frames may not always be necessary for scattering transforms to extract effective representations.

Simulation-based Inference of Reionization Parameters from 3D Tomographic 21 cm Light-cone Images

“…To mitigate these problems, it has been proposed to inject the inductive bias into CNNs with scattering transform (Mallat 2012a; Allys et al 2019;Cheng et al 2020;Pedersen et al 2022) and utilize the scattering transform to construct scattering or wavelet networks (Gauthier et al 2021;Pedersen et al 2022). The scattering transform employs the filters that have well-behaved mathematical structures, e.g.…”