Interpretability Techniques For Deep Learning 1
Metrics
Insertion AUC score
Results
Performance results of various models on this benchmark
Model Name | Insertion AUC score | Paper Title | Repository |
|---|---|---|---|
| Integrated Gradients | 0.3578 | Axiomatic Attribution for Deep Networks | |
| LIME | 0.5246 | "Why Should I Trust You?": Explaining the Predictions of Any Classifier | |
| Grad-CAM | 0.3721 | Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | |
| HSIC-Attribution | 0.5692 | Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure | |
| Kernel SHAP | 0.5246 | A Unified Approach to Interpreting Model Predictions | |
| RISE | 0.5703 | RISE: Randomized Input Sampling for Explanation of Black-box Models | |
| Saliency | 0.4632 | Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps |
0 of 7 row(s) selected.