In this work, we attempt to explain the prediction of any black-box classifier from an information-theoretic perspective. For this purpose, we propose two attribution maps: an information gain (IG) map and a point-wise mutual information (PMI) map. IG map provides a class-independent answer to "How informative is each pixel?", and PMI map offers a class-specific explanation by answering "How much does each pixel support a specific class?" In this manner, we propose (i) a theory-backed attribution method. The attribution (ii) provides both supporting and opposing explanations for each class and (iii) pinpoints most decisive parts in the image, not just the relevant objects. In addition, the method (iv) offers a complementary class-independent explanation. Lastly, the algorithmic enhancement in our method (v) improves faithfulness of the explanation in terms of a quantitative evaluation metric. We showed the five strengths of our method through various experiments on the ImageNet dataset. The code of the proposed method is available online.

中文翻译：

---

黑盒分类器的信息论视觉解释

在这项工作中，我们试图从信息论的角度解释任何黑盒分类器的预测。为此，我们提出了两种归因图：信息增益（IG）图和逐点互信息（PMI）图。IG 地图为“每个像素的信息量如何？”提供了与类无关的答案，而 PMI 地图通过回答“每个像素支持特定类的程度如何？”提供了特定于类的解释。通过这种方式，我们提出了 (i) 一种有理论支持的归因方法。属性 (ii) 为每个类别提供支持和反对的解释，并且 (iii) 指出图像中最具决定性的部分，而不仅仅是相关对象。此外，方法 (iv) 提供了与类无关的补充解释。最后，我们的方法 (v) 中的算法增强在定量评估指标方面提高了解释的忠实度。我们通过对 ImageNet 数据集的各种实验展示了我们方法的五个优势。所提出方法的代码可在线获得。