A Learnable ScatterNet: Locally Invariant Convolutional Layers
This work addresses image analysis researchers by offering an incremental improvement in hybrid network design.
The paper tackles the problem of integrating Scattering Transforms and Convolutional Neural Networks for image analysis by proposing a learnable ScatterNet with locally invariant layers, resulting in improved accuracy when added to CNNs or ScatterNets.
In this paper we explore tying together the ideas from Scattering Transforms and Convolutional Neural Networks (CNN) for Image Analysis by proposing a learnable ScatterNet. Previous attempts at tying them together in hybrid networks have tended to keep the two parts separate, with the ScatterNet forming a fixed front end and a CNN forming a learned backend. We instead look at adding learning between scattering orders, as well as adding learned layers before the ScatterNet. We do this by breaking down the scattering orders into single convolutional-like layers we call 'locally invariant' layers, and adding a learned mixing term to this layer. Our experiments show that these locally invariant layers can improve accuracy when added to either a CNN or a ScatterNet. We also discover some surprising results in that the ScatterNet may be best positioned after one or more layers of learning rather than at the front of a neural network.