Effective Semantic Pixel Labelling with Convolutional Networks and Conditional Random Fields
Abstract
Large amounts of available training data and increasing computing power have led to the recent success of deep convolutional neural networks (CNN) on a large number of applications. In this paper, we propose an effective semantic pixel labelling using CNN features, hand-crafted features and Conditional Random Fields (CRFs). Both CNN and hand-crafted features are applied to dense image patches to produce per-pixel class probabilities. The CRF infers a labelling that smooths regions while respecting the edges present in the imagery. The method is applied to the ISPRS 2D semantic labelling challenge dataset with competitive classification accuracy.
Cite
Text
Paisitkriangkrai et al. "Effective Semantic Pixel Labelling with Convolutional Networks and Conditional Random Fields." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301381Markdown
[Paisitkriangkrai et al. "Effective Semantic Pixel Labelling with Convolutional Networks and Conditional Random Fields." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/paisitkriangkrai2015cvprw-effective/) doi:10.1109/CVPRW.2015.7301381BibTeX
@inproceedings{paisitkriangkrai2015cvprw-effective,
title = {{Effective Semantic Pixel Labelling with Convolutional Networks and Conditional Random Fields}},
author = {Paisitkriangkrai, Sakrapee and Sherrah, Jamie and Janney, Pranam and van den Hengel, Anton},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2015},
pages = {36-43},
doi = {10.1109/CVPRW.2015.7301381},
url = {https://mlanthology.org/cvprw/2015/paisitkriangkrai2015cvprw-effective/}
}