Foundation Models, Self-Supervised Learning, and Explainable AI
EU-Philippines CoPhil Programme
| Capability | Traditional CNN | Foundation Model |
|---|---|---|
| Pre-training data | Task-specific (10–100k labeled) | Global EO archive (10^8+ patches) |
| Fine-tuning labels | 5–10k | 100–500 |
| Sensors handled | Usually single modality | Optical + SAR + DEM (model dependent) |
| Transfer across regions | Limited | High (learned invariances) |
| Compute demand (fine-tune) | Multi-GPU days | Single GPU < 2 hours |
| Technique | Works With | Insight Provided |
|---|---|---|
| SHAP | Tree models, tabular DL | Feature contribution per prediction |
| LIME | Any classifier/regressor | Local surrogate explaining single sample |
| Grad-CAM | CNN-based models | Heatmap of salient pixels/patches |
| Integrated Gradients | DNNs (incl. transformers) | Attribution along input path |

DAY 4 - Session 3 | Emerging AI in EO | 20-23 October 2025