Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure. (arXiv:2206.06219v3 [cs.CV] UPDATED)

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 …

arxiv making sense