DeepGCNs

Search this site DeepGCNs Can GCNs Go as Deep as CNNs? ICCV'2019 Oral p p p Figure 1. Our GCNs Network architecture for point clouds semantic segmentation. Left: Our framework consists of three blocks (one GCN Backbone Block, one Fusion Block and one MLP Prediction Block). Right: We mainly study three types of GCN Backbone Blocks i.e. PlainGCN, ResGCN and DenseGCN. There are two kinds of GCN skip connections vertex-wise additions and vertex-wise concatenations. k is the number of nearest neighbors in GCN layers. f is the number of the filters or hidden units. d is the dilation rate. Figure 2. Training Deep GCNs. Left: We present here the training loss for GCNs with 7, 14, 28, 56 layers, with and without residual connections. We note how adding more layers without residual connections translates to substantially higher loss. Right: In contrast, training GCNs with residual connections results in consistent stability for all depths. Abstract Convolutional Neural Networks (CNNs) achiev...

1 mentions: @udoooom
Date: 2019/08/10 03:47

Referring Tweets

@udoooom Can GCNs Go as Deep as CNNs?(ICCV'2019 Oral)のブランディングが凄い https://t.co/WkbuDbMeYp