DeepGCNs: Making GCNs Go as Deep as CNNs

10/15/2019
by   Guohao Li, et al.
108

Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, activity understanding, to name just a few. One key enabling factor for their great performance has been the ability to train very deep CNNs. Despite their huge success in many tasks, CNNs do not work well with non-Euclidean data which is prevalent in many real-world applications. Graph Convolutional Networks (GCNs) offer an alternative that allows for non-Eucledian data as input to a neural network similar to CNNs. While GCNs already achieve encouraging results, they are currently limited to shallow architectures with 2-4 layers due to vanishing gradients during training. This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. We show the benefit of deep GCNs with as many as 112 layers experimentally across various datasets and tasks. Specifically, we achieve state-of-the-art performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs. We believe that the insights in this work will open a lot of avenues for future research on GCNs and transfer to further tasks not explored in this work. The source code for this work is available for Pytorch and Tensorflow at https://github.com/lightaime/deep_gcns_torch and https://github.com/lightaime/deep_gcns respectively.

READ FULL TEXT

page 9

page 14

page 16

page 17

page 18

page 19

page 20

page 21

research
04/07/2019

Can GCNs Go as Deep as CNNs?

Convolutional Neural Networks (CNNs) achieve impressive results in a wid...
research
04/07/2019

Adaptively Connected Neural Networks

This paper presents a novel adaptively connected neural network (ACNet) ...
research
11/28/2016

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

State-of-the-art approaches for semantic image segmentation are built on...
research
05/04/2021

Multipath Graph Convolutional Neural Networks

Graph convolution networks have recently garnered a lot of attention for...
research
10/14/2022

Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again

Despite the enormous success of Graph Convolutional Networks (GCNs) in m...
research
12/24/2021

Deep ensembles in bioimage segmentation

Semantic segmentation consists in classifying each pixel of an image by ...
research
03/25/2020

What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective

Recent works have demonstrated that global covariance pooling (GCP) has ...

Please sign up or login with your details

Forgot password? Click here to reset