Search Results for author:
Found 2 papers, 0 papers with code
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation
This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of human expert feedback.
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
Explanations often take the form of a heatmap identifying input features (e. g. pixels) that are relevant to the model's decision.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
