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 ANOVA-like 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. Our implementation is available at https://github.com/paulnovello/HSIC-Attribution-Method.
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,从而通过RKHS 代表能力进行解释。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要快8倍,同时忠实。事实上,我们改进或匹配了黑箱和白箱归属方法对图像网络若干忠实度指标与最近各种模型结构的匹配性。重要的是,我们表明,这些进步可以被转换为高效和忠实地解释对象检测模型,如YOLOv4。 最后,我们扩展传统的归属方法,方法是提出一个新的核心内纳,使一个类似于ANOA 或Thotonal 重要分数的分数配置方法能够忠实于 HSICISIC/MIArusimum 的每个重要度互动,而不是我们现有的MIC-HASimal- 。