GAE reduces the faithfulness gap in dictionary-based explainers under distribution shift by geometrically realigning the ID dictionary to the OOD-active subspace, with a quadratic excess-loss bound.
Sanity checks for saliency maps
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
Uncertainty-aware extensions to Variational Information Pursuit (EUAV-IP and IUAV-IP) improve reliability and conciseness of concept-based predictions on five medical imaging datasets.
citing papers explorer
-
Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
GAE reduces the faithfulness gap in dictionary-based explainers under distribution shift by geometrically realigning the ID dictionary to the OOD-active subspace, with a quadratic excess-loss bound.
-
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
-
Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis
Uncertainty-aware extensions to Variational Information Pursuit (EUAV-IP and IUAV-IP) improve reliability and conciseness of concept-based predictions on five medical imaging datasets.