Adaptive Context Encoding Module for Semantic Segmentation

07/13/2019
by   Congcong Wang, et al.
0

The object sizes in images are diverse, therefore, capturing multiple scale context information is essential for semantic segmentation. Existing context aggregation methods such as pyramid pooling module (PPM) and atrous spatial pyramid pooling (ASPP) design different pooling size or atrous rate, such that multiple scale information is captured. However, the pooling sizes and atrous rates are chosen manually and empirically. In order to capture object context information adaptively, in this paper, we propose an adaptive context encoding (ACE) module based on deformable convolution operation to argument multiple scale information. Our ACE module can be embedded into other Convolutional Neural Networks (CNN) easily for context aggregation. The effectiveness of the proposed module is demonstrated on Pascal-Context and ADE20K datasets. Although our proposed ACE only consists of three deformable convolution blocks, it outperforms PPM and ASPP in terms of mean Intersection of Union (mIoU) on both datasets. All the experiment study confirms that our proposed module is effective as compared to the state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2018

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Spatial pyramid pooling module or encode-decoder structure are used in d...
research
07/04/2022

DeepPyramid: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos

Semantic segmentation in cataract surgery has a wide range of applicatio...
research
06/17/2017

Rethinking Atrous Convolution for Semantic Image Segmentation

In this work, we revisit atrous convolution, a powerful tool to explicit...
research
05/27/2015

Improving Spatial Codification in Semantic Segmentation

This paper explores novel approaches for improving the spatial codificat...
research
07/26/2023

Resolution-Aware Design of Atrous Rates for Semantic Segmentation Networks

DeepLab is a widely used deep neural network for semantic segmentation, ...
research
03/01/2023

DMSA: Dynamic Multi-scale Unsupervised Semantic Segmentation Based on Adaptive Affinity

The proposed method in this paper proposes an end-to-end unsupervised se...
research
03/23/2020

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

The convolution operation suffers from a limited receptive filed, while ...

Please sign up or login with your details

Forgot password? Click here to reset