Skip to content

Opening book details…

Can I read Explaining Image Classifiers with Multiscale Directional Image Representation on EtoBox?

Explaining Image Classifiers with Multiscale Directional Image Representation by Kolek, Stefan; Windesheim, Robert; Loarca, Hector Andrade; Kutyniok, Gitta; Levie, Ron is a scholarly article available to read on EtoBox.

What is Explaining Image Classifiers with Multiscale Directional Image Representation about?

Image classifiers are known to be difficult to interpret and therefore require explanation methods to understand their decisions. We present ShearletX, a novel mask explanation method for image classifiers based on the shearlet transform -- a multiscale directional image representation. Current mask explanation methods are regularized by smoothness constraints that protect against undesirable fine-grained explanation artifacts. However, the smoothness of a mask limits its ability to separate fine-detail patterns, that are relevant for the classifier, from nearby nuisance patterns, that do not affect the classifier. ShearletX solves this problem by avoiding smoothness regularization all together, replacing it by shearlet sparsity constraints. The resulting explanations consist of a few edges, textures, and smooth parts of the original image, that are the most relevant for the decision of the classifier. To support our method, we propose a mathematical definition for explanation artifacts and an information theoretic score to evaluate the quality of mask explanations. We demonstrate the superiority of ShearletX over previous mask based explanation methods using these new metrics, and

Author
Kolek, Stefan; Windesheim, Robert; Loarca, Hector Andrade; Kutyniok, Gitta; Levie, Ron
Published
2022
Language
EN

More by Kolek, Stefan; Windesheim, Robert; Loarca, Hector Andrade; Kutyniok, Gitta; Levie, Ron

Browse all works by Kolek, Stefan; Windesheim, Robert; Loarca, Hector Andrade; Kutyniok, Gitta; Levie, Ron