A deep learning pipeline for semantic facade segmentation
Radwa Fathalla and George Vogiatzis
Abstract
We propose an algorithm that provides a pixel-wise classification of building facades. Building facades provide a rich environment for testing semantic segmentation
techniques. They come in a variety of styles that reflect both appearance and layout characteristics. On the other hand, they exhibit a degree of stability in the arrangement of
structures across different instances. We integrate appearance and layout cues in a single
framework. The most likely label based on appearance is obtained through applying the
state-of-the-art deep convolution networks. This is further optimized through Restricted
Boltzmann Machines (RBM), applied on vertical and horizontal scanlines of facade models. Learning the probability distributions of the models via the RBMs is utilized in two
settings. Firstly, we use them in learning from pre-seen facade samples, in the traditional
training sense. Secondly, we learn from the test image at hand, in a way the allows the
transfer of visual knowledge of the scene from correctly classified areas to others. Experimentally, we are on par with the reported performance results.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.120
https://dx.doi.org/10.5244/C.31.120
Citation
Radwa Fathalla and George Vogiatzis. A deep learning pipeline for semantic facade segmentation. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 120.1-120.13. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_120,
title={A deep learning pipeline for semantic facade segmentation},
author={Radwa Fathalla and George Vogiatzis},
year={2017},
month={September},
pages={120.1-120.13},
articleno={120},
numpages={13},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.120},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.120}
}