DeepGCNs: Can GCNs Go As Deep As CNNs?

Citations Over TimeTop 1% of 2019 papers

Abstract

Convolutional Neural Networks (CNNs) achieve impressive performance in a wide variety of fields. Their success benefited from a massive boost when very deep CNN models were able to be reliably trained. Despite their merits, CNNs fail to properly address problems with non-Euclidean data. To overcome this challenge, Graph Convolutional Networks (GCNs) build graphs to represent non-Euclidean data, borrow concepts from CNNs, and apply them in training. GCNs show promising results, but they are usually limited to very shallow models due to the vanishing gradient problem. As a result, most state-of-the-art GCN models are no deeper than 3 or 4 layers. In this work, we present new ways to successfully train very deep GCNs. We do this by borrowing concepts from CNNs, specifically residual/dense connections and dilated convolutions, and adapting them to GCN architectures. Extensive experiments show the positive effect of these deep GCN frameworks. Finally, we use these new concepts to build a very deep 56-layer GCN, and show how it significantly boosts performance (+3.7% mIoU over state-of-the-art) in the task of point cloud semantic segmentation. We believe that the community can greatly benefit from this work, as it opens up many opportunities for advancing GCN-based research.

Related Papers

• → A Residual Correction Approach for Semi-supervised Semantic Segmentation(2021)17 cited
• → Implementing convolutional neural network model for prediction in medical imaging(2022)6 cited
• → Leaf Features Extraction for Plant Classification using CNN(2021)7 cited
• → Deep Convolution Neural Network for RBC Images(2022)2 cited
• → Deep Convolutional Neural Networks(2021)8 cited