Explanations for Occluded Images

Hana Chockler, Daniel Kroening, Youcheng Sun; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 1234-1243

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.

Related Material

[pdf] [arXiv]
[bibtex]
@InProceedings{Chockler_2021_ICCV, author = {Chockler, Hana and Kroening, Daniel and Sun, Youcheng}, title = {Explanations for Occluded Images}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {1234-1243} }