We propose a fairness-aware learning framework that mitigates intersecti...
Specialized documentation techniques have been developed to communicate ...
We survey a number of data visualization techniques for analyzing Comput...
Saliency maps have shown to be both useful and misleading for explaining...
Integrated Gradients has become a popular method for post-hoc model
inte...
We show how feature maps in convolutional networks are susceptible to sp...
In this paper we introduce a novel, unified, open-source model
interpret...
We propose a measure to compute class similarity in large-scale
classifi...
Most multi-class classifiers make their prediction for a test sample by
...
Convolutional Neural Networks (CNNs) currently achieve state-of-the-art
...