Abstract
Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object ofinterest 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 language | English |
---|---|
Title of host publication | Proceedings of International Conference on Computer Vision (ICCV) |
Publication status | Accepted/In press - Oct 2021 |