| Paper | Code | Insertion AUC score (ArcFace ResNet-101) | Deletion AUC score (ArcFace ResNet-101) | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Less is More: Fewer Interpretable Region via Submodular Subset Selection | ✓ Link | 0.5752 | 0.1054 | SMDL-Attribution (ICLR version) | 2024-02-14 |
| RISE: Randomized Input Sampling for Explanation of Black-box Models | ✓ Link | 0.5703 | 0.1444 | RISE | 2018-06-19 |
| Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure | ✓ Link | 0.5692 | 0.1151 | HSIC-Attribution | 2022-06-13 |
| A Unified Approach to Interpreting Model Predictions | ✓ Link | 0.5246 | 0.1409 | Kernel SHAP | 2017-05-22 |
| "Why Should I Trust You?": Explaining the Predictions of Any Classifier | ✓ Link | 0.5246 | 0.1484 | LIME | 2016-02-16 |
| Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps | ✓ Link | 0.4632 | 0.1453 | Saliency | 2013-12-20 |
| Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization | ✓ Link | 0.3721 | 0.2865 | Grad-CAM | 2016-10-07 |
| Axiomatic Attribution for Deep Networks | ✓ Link | 0.3578 | 0.0680 | Integrated Gradients | 2017-03-04 |