A Unified Approach to Interpreting Model Predictions

Benchmark Model Rank Results
image-attribution-on-celebaKernel SHAP#5Insertion AUC score (ArcFace ResNet-101): 0.5246
image-attribution-on-cub-200-2011-1Kernel SHAP#6Insertion AUC score (ResNet-101): 0.6763
image-attribution-on-vggface2Kernel SHAP#5Insertion AUC score (ArcFace ResNet-101): 0.6132
interpretability-techniques-for-deep-learning-1Kernel SHAP#4Insertion AUC score: 0.5246