DeDUCE: Generating Counterfactual Explanations At ScaleDownload PDF

21 Sept 2021, 14:51 (edited 15 Nov 2021)XAI 4 Debugging Workshop @ NEURIPS 2021 PosterReaders: Everyone
  • Keywords: Counterfactual explanations, XAI, Debugging
  • TL;DR: We introduce a novel, efficient algorithm providing counterfactual explanations for residual networks and compare its performance against baselines.
  • Abstract: 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.
0 Replies