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 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 experimentally that CartoonX is not only highly interpretable due to its piece-wise smooth nature but also particularly apt at explaining misclassifications.

A Rate-Distortion Framework for Explaining Black-box Model Decisions

“…Other explanation methods [20], [1], [2], and [3], have also previously exclusively operated in the pixel domain. In [11], we challenged this customary practice by successfully applying RDE in a wavelet basis, where sparsity translates into piece-wise smooth images (also called cartoon-like images). The novel explanation method was coined CartoonX [11] and extracts the relevant piece-wise smooth part of an image.…”

“…In [11], we challenged this customary practice by successfully applying RDE in a wavelet basis, where sparsity translates into piece-wise smooth images (also called cartoon-like images). The novel explanation method was coined CartoonX [11] and extracts the relevant piece-wise smooth part of an image. First, we review the Pixel RDE method and present experiments on the ImageNet dataset [4], which is commonly considered a challenging classification task.…”

“…We briefly illustrate the wavelet coefficients in Figure 2, which visualizes the discrete wavelet transform of an image. CartoonX [11] is a special case of the generalized RDE framework, particularly a special case of Example 2, and optimizes a sparse mask s ∈ [0, 1] n on the wavelet coefficients (see Figure 3c) so that the expected distortion D(x, s, V s , Φ) remains small. The obfuscation of an image x with a wavelet mask s and a distribution v ∼ V s on the wavelet coefficients is f (s h + (1 − s) v).…”

“…the signal more important for the classifier?". Most recently, in [11], we introduced CartoonX as a novel explanation method for image classifiers, answering the interpretation query "What is the relevant piece-wise smooth part of an image?" by applying RDE in the wavelet basis of images.…”