Parallel Fully Convolutional Network for Semantic Segmentation
Lists
Only you see this
Abstract
Fully convolutional networks (FCNs) have been widely applied for dense classification tasks such as semantic segmentation. As a large number of works based on FCNs are proposed, various semantic segmentation models have been improved significantly. However, duplicated upsampling and deconvolution operations in the FCNs will lead to information loss in semantic segmentation tasks and to problems such as ignoring the relationship between pixels and pixels and the lack of spatial consistency. In this study, we propose a parallel fully convolutional neural network that integrates holistically-nested edge detection (HED) network to capture image edge information, improving semantic segmentation performance. We carry out comprehensive experiments and achieve a better result on the PASCAL VOC 2012, PASCAL-Context and Cityscapes, comparing the results with some existing semantic segmentation methods.
BibTeX
@inproceedings{ji2021parallel,
author = {Jian Ji and Xiaocong Lu and Mai Luo and Minghui Yin and Qiguang Miao and Xiangzeng Liu},
title = {{Parallel Fully Convolutional Network for Semantic Segmentation}},
booktitle = {IEEE Access},
year = {2021},
url = {https://openreview.net/forum?id=GfbBoXeubZo},
}Loading related content...