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

by   Lichao Mou, et al.

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.



There are no comments yet.


page 1

page 6

page 7

page 8


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

Most current semantic segmentation approaches fall back on deep convolut...

Broadcasting Convolutional Network

While convolutional neural networks (CNNs) are widely used for handling ...

Convolutional Random Walk Networks for Semantic Image Segmentation

Most current semantic segmentation methods rely on fully convolutional n...

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

In a wide range of semantic segmentation tasks, fully convolutional neur...

GraNet: Global Relation-aware Attentional Network for ALS Point Cloud Classification

In this work, we propose a novel neural network focusing on semantic lab...

Hyperspectral Image Classification with Spatial Consistence Using Fully Convolutional Spatial Propagation Network

In recent years, deep convolutional neural networks (CNNs) have shown im...

HPRN: Holistic Prior-embedded Relation Network for Spectral Super-Resolution

Spectral super-resolution (SSR) refers to the hyperspectral image (HSI) ...
This week in AI

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