Believe the HiPe : hierarchical Perturbation for fast, robust, and model-agnostic saliency mapping
Abstract
Understanding the predictions made by Artificial Intelligence (AI) systems is becoming more and more important as deep learning models are used for increasingly complex and high-stakes tasks. Saliency mapping – a popular visual attribution method – is one important tool for this, but existing formulations are limited by either computational cost or architectural constraints. We therefore propose Hierarchical Perturbation, a very fast and completely model-agnostic method for interpreting model predictions with robust saliency maps. Using standard benchmarks and datasets, we show that our saliency maps are of competitive or superior quality to those generated by existing model-agnostic methods – and are over 20× faster to compute.
Citation
Cooper , J , Arandjelović , O & Harrison , D J 2022 , ' Believe the HiPe : hierarchical Perturbation for fast, robust, and model-agnostic saliency mapping ' , Pattern Recognition , vol. 129 , 108743 . https://doi.org/10.1016/j.patcog.2022.108743
Publication
Pattern Recognition
Status
Peer reviewed
ISSN
0031-3203Type
Journal article
Rights
Copyright © 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
Description
This work is supported by the Industrial Centre for AI Research in Digital Diagnostics (iCAIRD) which is funded by Innovate UK on behalf of UK Research and Innovation (UKRI) [project number: 104690].Collections
Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.