DeepGCNs: Making GCNs Go as Deep as CNNs

15 Oct 2019Guohao LiMatthias MüllerGuocheng QianItzel C. DelgadilloAbdulellah AbualshourAli ThabetBernard Ghanem

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 networks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification PPI ResMRGCN-28 F1 99.41 # 5
Node Classification PPI DenseMRGCN-14 F1 99.43 # 4
Semantic Segmentation S3DIS ResGCN-28 Mean IoU 60 # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet