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 CNNs... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Node Classification PPI DenseMRGCN-14 F1 99.43 # 3
Node Classification PPI ResMRGCN-28 F1 99.41 # 4
Semantic Segmentation S3DIS ResGCN-28 Mean IoU 60 # 2