Description
A wavelet scattering transform computes a translation invariant representation, which is stable to deformation, using a deep convolution network architecture. It computes non-linear invariants with modulus and averaging pooling functions. It helps to eliminate the image variability due to translation and is stable to deformations.
Image source: Bruna and Mallat
Papers Using This Method
Tackling the Accuracy-Interpretability Trade-off in a Hierarchy of Machine Learning Models for the Prediction of Extreme Heatwaves2024-10-01ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets2021-08-31Scattering Transform Based Image Clustering using Projection onto Orthogonal Complement2020-11-23Generative networks as inverse problems with fractional wavelet scattering networks2020-07-28Invariant Scattering Convolution Networks2012-03-05