Back to articles
Articles
Volume: 32 | Article ID: art00003
Image
Adaptive Context Encoding Module for Semantic Segmentation
  DOI :  10.2352/ISSN.2470-1173.2020.10.IPAS-027  Published OnlineJanuary 2020
Abstract

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) employ different pooling size or atrous rate, such that multiple scale information is captured. However, the pooling sizes and atrous rates are chosen empirically. Rethinking of ASPP leads to our observation that learnable sampling locations of the convolution operation can endow the network learnable fieldof- view, thus the ability of capturing object context information adaptively. Following this observation, in this paper, we propose an adaptive context encoding (ACE) module based on deformable convolution operation where sampling locations of the convolution operation are learnable. Our ACE module can be embedded into other Convolutional Neural Networks (CNNs) 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 experimental studies confirm that our proposed module is effective compared to the state-of-the-art methods.

Subject Areas :
Views 87
Downloads 0
 articleview.views 87
 articleview.downloads 0
  Cite this article 

Congcong Wang, Faouzi Alaya Cheikh, Azeddine Beghdadi, Ole Jakob Elle, "Adaptive Context Encoding Module for Semantic Segmentationin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Algorithms and Systems XVIII,  2020,  pp 27-1 - 27-7,  https://doi.org/10.2352/ISSN.2470-1173.2020.10.IPAS-027

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA