Samenvatting
We address the limitations of Deep learning models for 3D
geometry segmentation by using Conditional Random fields (CRF). We
show that CRFs can take advantage of the neighbouring structure of point
clouds to assist the learning of the Deep Learning models (DL). Our hybrid
PN-CRF model is able to learn more optimal weights by taking advantage
of equal-segmentation assignments to neighbouring points. As a result,
it increases the robustness in the model specially for segmentation tasks
where correctly detecting the boundaries between segmentations is very
important.
geometry segmentation by using Conditional Random fields (CRF). We
show that CRFs can take advantage of the neighbouring structure of point
clouds to assist the learning of the Deep Learning models (DL). Our hybrid
PN-CRF model is able to learn more optimal weights by taking advantage
of equal-segmentation assignments to neighbouring points. As a result,
it increases the robustness in the model specially for segmentation tasks
where correctly detecting the boundaries between segmentations is very
important.
| Originele taal-2 | English |
|---|---|
| Titel | European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning |
| Uitgeverij | Ciaco |
| Aantal pagina's | 6 |
| Volume | 27 |
| ISBN van geprinte versie | 978-287-587-065-0 |
| Status | Published - 24 apr 2019 |
| Evenement | European Symposium on Artificial Neural Networks 2019 - Brugge, Belgium Duur: 24 apr 2019 → 26 mrt 2020 |
Conference
| Conference | European Symposium on Artificial Neural Networks 2019 |
|---|---|
| Verkorte titel | ESANN |
| Land | Belgium |
| Stad | Brugge |
| Periode | 24/04/19 → 26/03/20 |