Interpretability
Monte Carlo Dropout
Introduced by Gal et al. in Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Classification | 9 | 6.08% |
| Active Learning | 8 | 5.41% |
| General Classification | 7 | 4.73% |
| Decision Making | 6 | 4.05% |
| Semantic Segmentation | 6 | 4.05% |
| Domain Adaptation | 5 | 3.38% |
| Text Classification | 5 | 3.38% |
| Image Classification | 5 | 3.38% |
| Object Detection | 4 | 2.70% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
