Pith. sign in

REVIEW

DeDUCE: Generating Counterfactual Explanations Efficiently

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2111.15639 v1 pith:WTB2GVAR submitted 2021-11-29 cs.CV cs.LGstat.ML

DeDUCE: Generating Counterfactual Explanations Efficiently

classification cs.CV cs.LGstat.ML
keywords algorithmcounterfactualcounterfactualsexplanationsimagebaselinesdeducegenerating
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original 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. The code for all experiments is available at https://github.com/benedikthoeltgen/DeDUCE.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.