Explanations for Occluded Images

Hana Chockler, Daniel Kroening, Youcheng Sun

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded. We present a novel, black-box algorithm for computing explanations that uses a principled approach based on causal theory. We have implemented the method in the DEEPCOVER tool. We obtain explanations that are much more accurate than those generated by the existing explanation tools on images with occlusions and observe a level of performance comparable to the state of the art when explaining images without occlusions.
Original languageEnglish
Title of host publication2021 International Conference on Computer Vision: Proceedings
DOIs
Publication statusPublished - 28 Feb 2022

Fingerprint

Dive into the research topics of 'Explanations for Occluded Images'. Together they form a unique fingerprint.

Cite this