Removing input features via a generative model to explain their attributions to classifier's decisionsDownload PDF

25 Sep 2019 (modified: 24 Dec 2019)ICLR 2020 Conference Blind SubmissionReaders: Everyone
  • Original Pdf: pdf
  • Abstract: Interpretability methods often measure the contribution of an input feature to an image classifier's decisions by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples. Instead, we propose to integrate a generative inpainter into three representative attribution map methods as a mechanism for removing input features. Compared to the original counterparts, our methods (1) generate more plausible counterfactual samples under the true data generating process; (2) are more robust to hyperparameter settings; and (3) localize objects more accurately. Our findings were consistent across both ImageNet and Places365 datasets and two different pairs of classifiers and inpainters.
  • Keywords: attribution maps, generative models, inpainting, counterfactual, explanations, interpretability, explainability
12 Replies