Fully convolutional networks for semantic segmentation

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks th...

Full description

Bibliographic Details

Published in:	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 3431 - 3440
Main Authors:	Long, Jonathan, Shelhamer, Evan, Darrell, Trevor
Format:	Conference Proceeding Journal Article
Language:	English
Published:	IEEE 01.06.2015
Subjects:	Adaptation models Computer architecture Construction Convolution Deconvolution Image segmentation Inference Networks Pattern recognition Segmentation Semantics State of the art Tasks Training
ISSN:	1063-6919, 1063-6919
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!