Cartoon Explanations of Image Classifiers

Kolek, Stefan; Nguyen, Duc Anh; Levie, Ron; Bruna, Joan und Kutyniok, Gitta (2022): Cartoon Explanations of Image Classifiers. 17th European Conference on Computer Vision (ECCV 2022), Tel Aviv, Israel, October 23–27, 2022. Avidan, Shai; Brostow, Gabriel; Cissé, Moustapha; Farinella, Giovanni Maria und Hassner, Tal (eds.) : In: Computer Vision – ECCV 2022, Lecture Notes in Computer Science Vol. 13672 Cham: Springer. pp. 443-458

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.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Mathematics, Computer Science and Statistics > Mathematics; Mathematics, Computer Science and Statistics > Mathematics > Bavarian Chair for Mathematical Foundations of Artificial Intelligence
• Subjects: 500 Science > 510 Mathematics
• ISSN: 0302-9743
• Place of Publication: Cham
• Language: English