3 papers
cs.LG2025
Measuring Model Performance in the Presence of an Intervention
Winston Chen, Michael W. Sjoding, Jenna Wiens
AI models are often evaluated based on their ability to predict the outcome of interest. However, in many AI for social impact applications, the presence of an intervention that af…
cs.HC2025
Selective Prediction Reduces the Negative Effects of Automation Bias Overall but Increases False Negatives
Sarah Jabbour, David Fouhey, Nikola Banovic +4
AI has the potential to augment human decision making. However, even high-performing models can produce inaccurate predictions when deployed. These inaccuracies, combined with auto…
cs.CV2024
DEPICT: Diffusion-Enabled Permutation Importance for Image Classification Tasks
Sarah Jabbour, Gregory Kondas, Ella Kazerooni +3
We propose a permutation-based explanation method for image classifiers. Current image-model explanations like activation maps are limited to instance-based explanations in the pix…