Image Representations

Scattering Transform

Introduced by Bruna et al. in Invariant Scattering Convolution Networks

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

Source: Invariant Scattering Convolution Networks


Paper Code Results Date Stars


Task Papers Share
Self-Supervised Learning 1 20.00%
Deep Clustering 1 20.00%
Image Clustering 1 20.00%
Image Generation 1 20.00%
General Classification 1 20.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign