Sidney Bender
YOU?
Author Swipe
View article: Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Towards Desiderata-Driven Design of Visual Counterfactual Explainers Open
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations, such as feature attribution, by revealing the specific da…
View article: Diffusion Counterfactuals for Image Regressors
Diffusion Counterfactuals for Image Regressors Open
Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations benefits from recent ad…
View article: Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation Open
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. Confounders are spurious features that…
View article: Cycle-Consistent World Models for Domain Independent Latent Imagination
Cycle-Consistent World Models for Domain Independent Latent Imagination Open
End-to-end autonomous driving seeks to solve the perception, decision, and control problems in an integrated way, which can be easier to generalize at scale and be more adapting to new scenarios. However, high costs and risks make it very …