Matches in SemOpenAlex for { <https://semopenalex.org/work/W2933565306> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2933565306 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." @default.
- W2933565306 created "2019-04-11" @default.
- W2933565306 creator A5024763828 @default.
- W2933565306 creator A5026143507 @default.
- W2933565306 creator A5032952197 @default.
- W2933565306 creator A5078633131 @default.
- W2933565306 date "2019-04-07" @default.
- W2933565306 modified "2023-10-10" @default.
- W2933565306 title "Can GCNs Go as Deep as CNNs" @default.
- W2933565306 hasPublicationYear "2019" @default.
- W2933565306 type Work @default.
- W2933565306 sameAs 2933565306 @default.
- W2933565306 citedByCount "18" @default.
- W2933565306 countsByYear W29335653062019 @default.
- W2933565306 countsByYear W29335653062020 @default.
- W2933565306 countsByYear W29335653062021 @default.
- W2933565306 crossrefType "posted-content" @default.
- W2933565306 hasAuthorship W2933565306A5024763828 @default.
- W2933565306 hasAuthorship W2933565306A5026143507 @default.
- W2933565306 hasAuthorship W2933565306A5032952197 @default.
- W2933565306 hasAuthorship W2933565306A5078633131 @default.
- W2933565306 hasConcept C108583219 @default.
- W2933565306 hasConcept C111919701 @default.
- W2933565306 hasConcept C11413529 @default.
- W2933565306 hasConcept C119857082 @default.
- W2933565306 hasConcept C132525143 @default.
- W2933565306 hasConcept C154945302 @default.
- W2933565306 hasConcept C155512373 @default.
- W2933565306 hasConcept C2522767166 @default.
- W2933565306 hasConcept C2984842247 @default.
- W2933565306 hasConcept C41008148 @default.
- W2933565306 hasConcept C79974875 @default.
- W2933565306 hasConcept C80444323 @default.
- W2933565306 hasConcept C81363708 @default.
- W2933565306 hasConcept C89600930 @default.
- W2933565306 hasConceptScore W2933565306C108583219 @default.
- W2933565306 hasConceptScore W2933565306C111919701 @default.
- W2933565306 hasConceptScore W2933565306C11413529 @default.
- W2933565306 hasConceptScore W2933565306C119857082 @default.
- W2933565306 hasConceptScore W2933565306C132525143 @default.
- W2933565306 hasConceptScore W2933565306C154945302 @default.
- W2933565306 hasConceptScore W2933565306C155512373 @default.
- W2933565306 hasConceptScore W2933565306C2522767166 @default.
- W2933565306 hasConceptScore W2933565306C2984842247 @default.
- W2933565306 hasConceptScore W2933565306C41008148 @default.
- W2933565306 hasConceptScore W2933565306C79974875 @default.
- W2933565306 hasConceptScore W2933565306C80444323 @default.
- W2933565306 hasConceptScore W2933565306C81363708 @default.
- W2933565306 hasConceptScore W2933565306C89600930 @default.
- W2933565306 hasLocation W29335653061 @default.
- W2933565306 hasOpenAccess W2933565306 @default.
- W2933565306 hasPrimaryLocation W29335653061 @default.
- W2933565306 hasRelatedWork W2139823104 @default.
- W2933565306 hasRelatedWork W2153959628 @default.
- W2933565306 hasRelatedWork W2194775991 @default.
- W2933565306 hasRelatedWork W2606202972 @default.
- W2933565306 hasRelatedWork W2811124557 @default.
- W2933565306 hasRelatedWork W2905224888 @default.
- W2933565306 hasRelatedWork W2950898568 @default.
- W2933565306 hasRelatedWork W2962767366 @default.
- W2933565306 hasRelatedWork W2963858333 @default.
- W2933565306 hasRelatedWork W2964015378 @default.
- W2933565306 hasRelatedWork W2964051675 @default.
- W2933565306 hasRelatedWork W2964114465 @default.
- W2933565306 hasRelatedWork W2964121744 @default.
- W2933565306 hasRelatedWork W2964124573 @default.
- W2933565306 hasRelatedWork W2964311892 @default.
- W2933565306 hasRelatedWork W2964321699 @default.
- W2933565306 hasRelatedWork W2968397098 @default.
- W2933565306 hasRelatedWork W3021719071 @default.
- W2933565306 hasRelatedWork W3100848837 @default.
- W2933565306 hasRelatedWork W4210257598 @default.
- W2933565306 isParatext "false" @default.
- W2933565306 isRetracted "false" @default.
- W2933565306 magId "2933565306" @default.
- W2933565306 workType "article" @default.