A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes

04/11/2019
by   Lichao Mou, et al.
0

Most current semantic segmentation approaches fall back on deep convolutional neural networks (CNNs). However, their use of convolution operations with local receptive fields causes failures in modeling contextual spatial relations. Prior works have sought to address this issue by using graphical models or spatial propagation modules in networks. But such models often fail to capture long-range spatial relationships between entities, which leads to spatially fragmented predictions. Moreover, recent works have demonstrated that channel-wise information also acts a pivotal part in CNNs. In this work, we introduce two simple yet effective network units, the spatial relation module and the channel relation module, to learn and reason about global relationships between any two spatial positions or feature maps, and then produce relation-augmented feature representations. The spatial and channel relation modules are general and extensible, and can be used in a plug-and-play fashion with the existing fully convolutional network (FCN) framework. We evaluate relation module-equipped networks on semantic segmentation tasks using two aerial image datasets, which fundamentally depend on long-range spatial relational reasoning. The networks achieve very competitive results, bringing significant improvements over baselines.

READ FULL TEXT

page 1

page 6

page 7

page 8

research
04/11/2019

A Relation-Augmented Fully Convolutional Network for Semantic Segmentationin Aerial Scenes

Most current semantic segmentation approaches fall back on deep convolut...
research
05/24/2016

Convolutional Random Walk Networks for Semantic Image Segmentation

Most current semantic segmentation methods rely on fully convolutional n...
research
12/07/2017

Broadcasting Convolutional Network

While convolutional neural networks (CNNs) are widely used for handling ...
research
08/23/2018

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

In a wide range of semantic segmentation tasks, fully convolutional neur...
research
10/30/2018

Encoded Hourglass Network for Semantic Segmentation of High Resolution Aerial Imagery

Fully Convolutional Network (FCN) has been widely used in recent work fo...
research
12/08/2021

Fully Attentional Network for Semantic Segmentation

Recent non-local self-attention methods have proven to be effective in c...
research
04/27/2020

Distance Guided Channel Weighting for Semantic Segmentation

Recent works have achieved great success in improving the performance of...

Please sign up or login with your details

Forgot password? Click here to reset