TY - GEN
T1 - CANNET
T2 - IEEE International Conference on Image Processing, ICIP 2015
AU - Ran, Lingyan
AU - Zhang, Yanning
AU - Hua, Gang
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/9
Y1 - 2015/12/9
N2 - 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.
AB - 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.
KW - context aware module
KW - Semantic segmentation
KW - sparse kernel
UR - https://www.scopus.com/pages/publications/84956648452
U2 - 10.1109/ICIP.2015.7351692
DO - 10.1109/ICIP.2015.7351692
M3 - 会议稿件
AN - SCOPUS:84956648452
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 4669
EP - 4673
BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PB - IEEE Computer Society
Y2 - 27 September 2015 through 30 September 2015
ER -