research
∙
12/26/2022
Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
We propose a fairness-aware learning framework that mitigates intersecti...
share
research
∙
04/27/2022
Prescriptive and Descriptive Approaches to Machine-Learning Transparency
Specialized documentation techniques have been developed to communicate ...
research
∙
04/19/2022
A Tour of Visualization Techniques for Computer Vision Datasets
We survey a number of data visualization techniques for analyzing Comput...
research
∙
06/08/2021
Investigating sanity checks for saliency maps with image and text classification
Saliency maps have shown to be both useful and misleading for explaining...
research
∙
10/23/2020
Investigating Saturation Effects in Integrated Gradients
Integrated Gradients has become a popular method for post-hoc model inte...
research
∙
10/05/2020
Mind the Pad – CNNs can Develop Blind Spots
We show how feature maps in convolutional networks are susceptible to sp...
research
∙
09/16/2020
Captum: A unified and generic model interpretability library for PyTorch
In this paper we introduce a novel, unified, open-source model interpret...
research
∙
07/12/2020
Visualizing Classification Structure in Deep Neural Networks
We propose a measure to compute class similarity in large-scale classifi...
research
∙
11/18/2017
Prediction Scores as a Window into Classifier Behavior
Most multi-class classifiers make their prediction for a test sample by ...
research
∙
10/17/2017