Cartoon Explanations of Image Classifiers
Abstract
We present CartoonX (Cartoon Explanation), a novel model-agnostic explanation method tailored towards image classifiers and based on the rate-distortion explanation (RDE) framework. Natural images are roughly piece-wise smooth signals---also called cartoon-like images---and tend to be sparse in the wavelet domain. CartoonX is the first explanation method to exploit this by requiring its explanations to be sparse in the wavelet domain, thus extracting the relevant piece-wise smooth part of an image instead of relevant pixel-sparse regions. We demonstrate that CartoonX can reveal novel valuable explanatory information, particularly for misclassifications. Moreover, we show that CartoonX achieves a lower distortion with fewer coefficients than state-of-the-art methods.
Cite
Text
Kolek et al. "Cartoon Explanations of Image Classifiers." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19775-8_26Markdown
[Kolek et al. "Cartoon Explanations of Image Classifiers." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/kolek2022eccv-cartoon/) doi:10.1007/978-3-031-19775-8_26BibTeX
@inproceedings{kolek2022eccv-cartoon,
title = {{Cartoon Explanations of Image Classifiers}},
author = {Kolek, Stefan and Nguyen, Duc Anh and Levie, Ron and Bruna, Joan and Kutyniok, Gitta},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19775-8_26},
url = {https://mlanthology.org/eccv/2022/kolek2022eccv-cartoon/}
}