CANNET: Context aware nonlocal convolutional networks for semantic image segmentation

Lingyan Ran, Yanning Zhang, Gang Hua

科研成果: 书/报告/会议事项章节会议稿件同行评审

9 引用 (Scopus)

摘要

Semantic segmentation has long been a hot topic, most methods are the region based method, which lost connection information to their neighbors. In this paper we propose to encode context information into convolutional networks on this semantic labeling task. Firstly, we propose the nonlocal convolution kernel, which extracts feature from larger neighbor regions without introducing more parameters. Then we build up a context aware module, which takes both local patch and nonlocal neighbor information into account. At last we embed the module into convolutional networks and tested the improvement on benchmark datasets.

源语言英语
主期刊名2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
出版商IEEE Computer Society
4669-4673
页数5
ISBN(电子版)9781479983391
DOI
出版状态已出版 - 9 12月 2015
活动IEEE International Conference on Image Processing, ICIP 2015 - Quebec City, 加拿大
期限: 27 9月 201530 9月 2015

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
2015-December
ISSN(印刷版)1522-4880

会议

会议IEEE International Conference on Image Processing, ICIP 2015
国家/地区加拿大
Quebec City
时期27/09/1530/09/15

指纹

探究 'CANNET: Context aware nonlocal convolutional networks for semantic image segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此