Hierarchical joint-guided networks for semantic image segmentation
Chien-Yao Wang, Jyun-Hong Li, Seksan Mathulaprangsan, Chin-Chin Chiang, Jia-Ching Wang
Abstract
Semantic image segmentation is now an exciting area of research owing to its various useful applications in daily life. This paper introduces a hierarchical joint-guided network (HJGN) which is mainly composed of proposed hierarchical joint learning convolutional networks (HJLCNs) and proposed joint-guided and making networks (JGMNs). HJLCNs exhibit high robustness in the segmentation of unseen objects that are not contained in training categories. JGMNs are very effective in filling holes and preventing incorrect segmentation predictions. The proposed HJGNs outperform the state-of-the-art methods on the PASCAL VOC 2012 testing set, reaching a mean IU of 80.4%.
BibTeX
@inproceedings{icassp2017_hierarchicaljoin,
title = {Hierarchical joint-guided networks for semantic image segmentation},
author = {Chien-Yao Wang and Jyun-Hong Li and Seksan Mathulaprangsan and Chin-Chin Chiang and Jia-Ching Wang},
booktitle = {ICASSP 2017},
year = {2017}
}