Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network

by   Naina Dhingra, et al.

We present Border-SegGCN, a novel architecture to improve semantic segmentation by refining the border outline using graph convolutional networks (GCN). The semantic segmentation network such as Unet or DeepLabV3+ is used as a base network to have pre-segmented output. This output is converted into a graphical structure and fed into the GCN to improve the border pixel prediction of the pre-segmented output. We explored and studied the factors such as border thickness, number of edges for a node, and the number of features to be fed into the GCN by performing experiments. We demonstrate the effectiveness of the Border-SegGCN on the CamVid and Carla dataset, achieving a test set performance of 81.96 reported state of the art mIoU achieved on CamVid dataset by 0.404



There are no comments yet.


page 2

page 3

page 4

page 5

page 6

page 8


SStaGCN: Simplified stacking based graph convolutional networks

Graph convolutional network (GCN) is a powerful model studied broadly in...

OD-GCN object detection by knowledge graph with GCN

Classical object detection frameworks lack of utilizing objects' surroun...

SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks

We introduce SketchGCN, a graph convolutional neural network for semanti...

Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding

Automatic building extraction from optical imagery remains a challenge d...

Dual Graph Convolutional Network for Semantic Segmentation

Exploiting long-range contextual information is key for pixel-wise predi...

Classification of Computer Aided Engineering (CAE) Parts Using Graph Convolutional Networks

CAE engineers work with hundreds of parts spread across multiple body mo...

A Multiscale Graph Convolutional Network Using Hierarchical Clustering

The information contained in hierarchical topology, intrinsic to many ne...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.