Image Classification with Hierarchical Multigraph Networks

07/21/2019
by   Boris Knyazev, et al.
4

Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data. Despite being general, GCNs are admittedly inferior to convolutional neural networks (CNNs) when applied to vision tasks, mainly due to the lack of domain knowledge that is hardcoded into CNNs, such as spatially oriented translation invariant filters. However, a great advantage of GCNs is the ability to work on irregular inputs, such as superpixels of images. This could significantly reduce the computational cost of image reasoning tasks. Another key advantage inherent to GCNs is the natural ability to model multirelational data. Building upon these two promising properties, in this work, we show best practices for designing GCNs for image classification; in some cases even outperforming CNNs on the MNIST, CIFAR-10 and PASCAL image datasets.

READ FULL TEXT

page 2

page 5

page 8

research
12/27/2016

Steerable CNNs

It has long been recognized that the invariance and equivariance propert...
research
07/24/2021

Spatial Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have recently be- come the primary ...
research
05/11/2020

Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices

Convolutional Neural Networks, or CNNs, are undoubtedly the state of the...
research
08/06/2020

Graph Convolutional Networks for Hyperspectral Image Classification

Convolutional neural networks (CNNs) have been attracting increasing att...
research
07/13/2023

On the ability of CNNs to extract color invariant intensity based features for image classification

Convolutional neural networks (CNNs) have demonstrated remarkable succes...
research
07/25/2019

Convolutional Neural Networks on Randomized Data

Convolutional Neural Networks (CNNs) are build specifically for computer...
research
09/22/2014

Spatially-sparse convolutional neural networks

Convolutional neural networks (CNNs) perform well on problems such as ha...

Please sign up or login with your details

Forgot password? Click here to reset