Published January 16, 2025
| Version v2
Publication
Open
Space-scale Exploration of the Poor Reliability of Deep Learning Models: the Case of the Remote Sensing of Rooftop Photovoltaic Systems
Creators
-
1.
École Nationale Supérieure des Mines de Paris
-
2.
Université Paris Sciences et Lettres
- 3. Réseau de transport d'électricité
Description
Models weights for the replication of the results of the paper "Space-scale Exploration of the Poor Reliability of Deep Learning Models: the Case of the Remote Sensing of Rooftop Photovoltaic Systems".
Code for the replication of the results is accessible at https://github.com/gabrielkasmi/robust_pv_mapping.
The weight for the Scattering transform are organized in google and ign folders, for models trained on Google and IGN respectively. The depth of the models (m=1 to m=3) are indicated in the model names.
Files
models.zip
Additional details
Related works
- Is supplement to
- Conference paper: arXiv:2309.12214 (arXiv)
- Preprint: arXiv:2408.07828 (arXiv)
Software
- Repository URL
- https://github.com/gabrielkasmi/robust_pv_mapping
- Development Status
- Active