1 code implementation • 7 Mar 2019 • Fergal Cotter, Nick Kingsbury
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.
1 code implementation • 14 Nov 2018 • Fergal Cotter, Nick Kingsbury
We are stimulated by both Mallat's scattering transform and the idea of filtering in the Fourier domain.
no code implementations • 9 Feb 2018 • Amarjot Singh, Nick Kingsbury
This paper proposes a generative ScatterNet hybrid deep learning (G-SHDL) network for semantic image segmentation.
no code implementations • 5 Sep 2017 • Fergal Cotter, Nick Kingsbury
These complex patterns may be useful for texture classification, but are quite dissimilar from the patterns visualized in second and third layers of Convolutional Neural Networks (CNNs) - the current state of the art Image Classifiers.
no code implementations • 30 Aug 2017 • Amarjot Singh, Nick Kingsbury
The paper proposes the ScatterNet Hybrid Deep Learning (SHDL) network that extracts invariant and discriminative image representations for object recognition.
no code implementations • 30 Aug 2017 • Amarjot Singh, Nick Kingsbury
The ScatterNet extracts edge based invariant representations that are used by the later layers of the CNN to learn high-level features.
no code implementations • 10 Feb 2017 • Amarjot Singh, Nick Kingsbury
This paper introduces a Deep Scattering network that utilizes Dual-Tree complex wavelets to extract translation invariant representations from an input signal.
no code implementations • 10 Feb 2017 • Amarjot Singh, Nick Kingsbury
We introduce a ScatterNet that uses a parametric log transformation with Dual-Tree complex wavelets to extract translation invariant representations from a multi-resolution image.