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.
翻译:本文介绍了基于Hilbert-Schmidt独立标准(HSIC)的新的高效黑箱归属方法(HSIC),这是基于复制 Kernel Hilbert 空间(RKHS) 的一项依赖性措施。 HSIC 测量输入图像区域与基于分布内嵌的模型输出之间的依赖性。 因此,它提供了由 RKHS 代表能力补充的解释。 HSIC 可以非常高效地估算,大大降低计算成本,与其他黑箱归属方法相比,我们实验显示, HSIC 比先前的最佳黑箱归属方法快8倍,同时忠实。 事实上,我们改进或匹配了图像网络上若干忠实度指标的最新模式结构。 重要的是,我们表明这些进展可以被移植到高效和忠实地解释对象检测模型,如YOLOv4。 最后,我们扩展了传统归属方法,提出了一个新的内核,使得基于 HSIC 的重要分数能够或多位配置。 事实上,我们不仅能够评估每个图像互动的重要性,而且能够评估每个图像组合的重要性。