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 other state-of-the-art methods.
翻译:我们展示了卡通X(Cartonon Professoration),这是一个针对图像分类者并基于比例扭曲解释(RDE)框架的新颖的模型 -- -- 不可知解释方法。自然图像大致是零星的光滑信号 -- -- 也被称为卡通图像 -- -- 并且往往在波盘域中稀释。卡通X是利用它的第一个解释方法,要求其解释在波盘域中稀释,从而提取图像的相关片段光滑部分,而不是相关的像素吸食区域。我们证明,卡通X可以揭示新的有价值的解释信息,特别是分类错误的解释。此外,我们还显示,卡通X的扭曲现象比其他最先进的方法少,其系数也较低。