Generalizing the Convolution Operator to extend CNNs to Irregular Domains

06/03/2016
by   Jean-Charles Vialatte, et al.
0

Convolutional Neural Networks (CNNs) have become the state-of-the-art in supervised learning vision tasks. Their convolutional filters are of paramount importance for they allow to learn patterns while disregarding their locations in input images. When facing highly irregular domains, generalized convolutional operators based on an underlying graph structure have been proposed. However, these operators do not exactly match standard ones on grid graphs, and introduce unwanted additional invariance (e.g. with regards to rotations). We propose a novel approach to generalize CNNs to irregular domains using weight sharing and graph-based operators. Using experiments, we show that these models resemble CNNs on regular domains and offer better performance than multilayer perceptrons on distorded ones.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/27/2017

Convolutional neural networks on irregular domains through approximate translations on inferred graphs

We propose a generalization of convolutional neural networks (CNNs) to i...
research
06/30/2016

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

In this work, we are interested in generalizing convolutional neural net...
research
02/13/2019

Classifying Signals on Irregular Domains via Convolutional Cluster Pooling

We present a novel and hierarchical approach for supervised classificati...
research
09/28/2016

Graph Based Convolutional Neural Network

The benefit of localized features within the regular domain has given ri...
research
03/06/2018

MIMO Graph Filters for Convolutional Neural Networks

Superior performance and ease of implementation have fostered the adopti...
research
07/18/2022

SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data

Convolutional Neural Networks have revolutionized vision applications. T...
research
08/02/2019

An Underparametrized Deep Decoder Architecture for Graph Signals

While deep convolutional architectures have achieved remarkable results ...

Please sign up or login with your details

Forgot password? Click here to reset