Explaining Image Classifiers with Multiscale Directional Image Representation

by   Stefan Kolek, et al.

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 present exemplary situations where separating fine-detail patterns allows explaining phenomena that were not explainable before.


page 2

page 5

page 7

page 9


Cartoon Explanations of Image Classifiers

We present CartoonX (Cartoon Explanation), a novel model-agnostic explan...

NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning

Deep Neural Networks (DNNs) deliver state-of-the-art performance in many...

Fine-Grained and High-Faithfulness Explanations for Convolutional Neural Networks

Recently, explaining CNNs has become a research hotspot. CAM (Class Acti...

Compositional Explanations for Image Classifiers

Existing algorithms for explaining the output of image classifiers perfo...

A framework for step-wise explaining how to solve constraint satisfaction problems

We explore the problem of step-wise explaining how to solve constraint s...

Enriching Visual with Verbal Explanations for Relational Concepts – Combining LIME with Aleph

With the increasing number of deep learning applications, there is a gro...

Please sign up or login with your details

Forgot password? Click here to reset