Singapore Institute of Technology
2 files

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

Download all (3.3 MB)
conference contribution
posted on 2023-11-08, 06:11 authored by Alexander Binder, Leander Weber, Sebastian Lapuschkin, Gregoire Montavon, Klaus-Robert Müller, Wojciech Samek

While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing can be overinterpreted if regarded as a primary criterion for selecting or discarding explanation methods. To address shortcomings of this test, we start by observing an experimental gap in the ranking of explanation methods between randomization-based sanity checks [1] and model output faithfulness measures (e.g. [20]). We identify limitations of model-randomization-based sanity checks for the purpose of evaluating explanations. Firstly, we show that uninformative attribution maps created with zero pixel-wise covariance easily achieve high scores in this type of checks. Secondly, we show that top-down model randomization preserves scales of forward pass activations with high probability. That is, channels with large activations have a high probility to contribute strongly to the output, even after randomization of the network on top of them. Hence, explanations after randomization can only be expected to differ to a certain extent. This explains the observed experimental gap. In summary, these results demonstrate the inadequacy of model-randomization-based sanity checks as a criterion to rank attribution methods.


Journal/Conference/Book title

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 17-24 June 2023, Vancouver, BC, Canada.

Publication date



  • Post-print

Sub-Item type

  • Magazine article

Usage metrics



    Ref. manager