DeDUCE: Generating Counterfactual Explanations Efficiently
This addresses the need for scalable counterfactual explanations in image classification, though it is incremental as it builds on existing methods with a focus on efficiency.
The paper tackles the problem of generating counterfactual explanations for image classifiers by developing a new algorithm that efficiently produces explanations with low computational cost, resulting in counterfactuals that are much closer to the original inputs while maintaining comparable realism to baselines.
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. The code for all experiments is available at https://github.com/benedikthoeltgen/DeDUCE.