Black-Box Saliency Map Generation Using Bayesian Optimisation

Mamuku Mokuwe, Michael Burke, Anna Sergeevna Bosman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require access to model parameters. This work proposes an approach for saliency map generation for black-box models, where no access to model parameters is available, using a Bayesian optimisation sampling method. The approach aims to find the global salient image region responsible for a particular (black-box) model’s prediction. This is achieved by a sampling-based approach to model perturbations that seeks to localise salient regions of an image to the black-box model. Results show that the proposed approach to saliency map generation outperforms grid-based perturbation approaches, and performs similarly to gradient-based approaches which require access to model parameters.
Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks (IJCNN)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages8
ISBN (Electronic)978-1-7281-6926-2
ISBN (Print)978-1-7281-6927-9
DOIs
Publication statusPublished - 28 Sep 2020
EventThe International Joint Conference on Neural Networks 2020 - Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020
https://wcci2020.org/

Publication series

Name
PublisherIEEE
ISSN (Print)2161-4393
ISSN (Electronic)2161-4407

Conference

ConferenceThe International Joint Conference on Neural Networks 2020
Abbreviated titleIJCNN 2020
Country/TerritoryUnited Kingdom
CityGlasgow
Period19/07/2024/07/20
Internet address

Fingerprint

Dive into the research topics of 'Black-Box Saliency Map Generation Using Bayesian Optimisation'. Together they form a unique fingerprint.

Cite this