This paper presents a new efficient black-box attribution method based on Hilbert-Schmidt Independence Criterion (HSIC), a dependence measure based on Reproducing Kernel Hilbert Spaces (RKHS). HSIC measures the dependence between regions of an input image and the output of a model based on kernel embeddings of distributions. It thus provides explanations enriched by RKHS representation capabilities. HSIC can be estimated very efficiently, significantly reducing the computational cost compared to other black-box attribution methods. Our experiments show that HSIC is up to 8 times faster than the previous best black-box attribution methods while being as faithful. Indeed, we improve or match the state-of-the-art of both black-box and white-box attribution methods for several fidelity metrics on Imagenet with various recent model architectures. Importantly, we show that these advances can be transposed to efficiently and faithfully explain object detection models such as YOLOv4. Finally, we extend the traditional attribution methods by proposing a new kernel enabling an orthogonal decomposition of importance scores based on HSIC, allowing us to evaluate not only the importance of each image patch but also the importance of their pairwise interactions.

中文翻译：

---

理解依赖：使用依赖度量的有效黑盒解释

本文提出了一种新的基于希尔伯特-施密特独立准则（HSIC）的高效黑盒归因方法，这是一种基于再生核希尔伯特空间（RKHS）的依赖度量。HSIC 测量输入图像区域与基于分布的内核嵌入的模型输出之间的依赖性。因此，它提供了由 RKHS 表示能力丰富的解释。HSIC 可以非常有效地估计，与其他黑盒归因方法相比，显着降低了计算成本。我们的实验表明，HSIC 比以前最好的黑盒归因方法快 8 倍，同时保持忠实。事实上，我们改进或匹配了 Imagenet 上的几个保真度指标的黑盒和白盒归因方法的最新技术，以及各种最近的模型架构。重要的是，我们表明这些进步可以转化为有效和忠实地解释对象检测模型，例如 YOLOv4。最后，我们通过提出一个新的内核来扩展传统的归因方法，该内核能够基于 HSIC 对重要性分数进行正交分解，从而使我们不仅可以评估每个图像块的重要性，还可以评估它们成对交互的重要性。