DCANet: Dense Context-Aware Network for Semantic Segmentation

04/06/2021
by   Yifu Liu, et al.
0

As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes. In contrast to some previous works utilizing the multi-scale context fusion, we propose a novel module, named Dense Context-Aware (DCA) module, to adaptively integrate local detail information with global dependencies. Driven by the contextual relationship, the DCA module can better achieve the aggregation of context information to generate more powerful features. Furthermore, we deliberately design two extended structures based on the DCA modules to further capture the long-range contextual dependency information. By combining the DCA modules in cascade or parallel, our networks use a progressive strategy to improve multi-scale feature representations for robust segmentation. We empirically demonstrate the promising performance of our approach (DCANet) with extensive experiments on three challenging datasets, including PASCAL VOC 2012, Cityscapes, and ADE20K.

READ FULL TEXT

page 3

page 20

page 21

page 24

research
04/20/2021

CTNet: Context-based Tandem Network for Semantic Segmentation

Contextual information has been shown to be powerful for semantic segmen...
research
11/22/2017

Neuron-level Selective Context Aggregation for Scene Segmentation

Contextual information provides important cues for disambiguating visual...
research
08/26/2019

Gated Convolutional Networks with Hybrid Connectivity for Image Classification

We design a highly efficient architecture called Gated Convolutional Net...
research
01/19/2020

Gated Path Selection Network for Semantic Segmentation

Semantic segmentation is a challenging task that needs to handle large s...
research
08/30/2022

Probing Contextual Diversity for Dense Out-of-Distribution Detection

Detection of out-of-distribution (OoD) samples in the context of image c...
research
09/20/2019

ACFNet: Attentional Class Feature Network for Semantic Segmentation

Recent works have made great progress in semantic segmentation by exploi...
research
04/05/2021

Hierarchical Pyramid Representations for Semantic Segmentation

Understanding the context of complex and cluttered scenes is a challengi...

Please sign up or login with your details

Forgot password? Click here to reset