Timezone: »

 
[S7] DeDUCE: Generating Counterfactual Explanations At Scale
Benedikt Höltgen · Lisa Schut · Jan Brauner · Yarin Gal

Tue Dec 14 09:09 AM -- 09:12 AM (PST) @
in eXplainable AI approaches for debugging and diagnosis »
Event URL: https://openreview.net/forum?id=-GyS3kjKMg9 »

When an image classifier outputs a wrong class label, it can be helpful to see what changes in the image would lead to a correct classification. This is the aim of algorithms generating counterfactual explanations. However, there is no easily scalable method to generate such counterfactuals. We develop a new algorithm providing counterfactual explanations for large image classifiers trained with spectral normalisation at low computational cost. We empirically compare this algorithm against baselines from the literature; our novel algorithm consistently finds counterfactuals that are much closer to the original inputs. At the same time, the realism of these counterfactuals is comparable to the baselines.

Author Information

Benedikt Höltgen (University of Oxford)
Lisa Schut (University of Oxford)
Jan Brauner (University of Oxford)
Yarin Gal (University of Oxford)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors