Investigating Neighborhood Generation Methods for Explanations of Obscure Image Classifiers

You are here

AttachmentSize
PDF icon pakdd2019investigating.pdf3.21 MB
TitleInvestigating Neighborhood Generation Methods for Explanations of Obscure Image Classifiers
Publication TypeConference Paper
Year of Publication2019
AuthorsGuidotti, R, Monreale, A, Cariaggi, L
Conference NamePacific-Asia Conference on Knowledge Discovery and Data Mining
PublisherSpringer
AbstractGiven the wide use of machine learning approaches based on opaque prediction models, understanding the reasons behind decisions of black box decision systems is nowadays a crucial topic. We address the problem of providing meaningful explanations in the widely-applied image classification tasks. In particular, we explore the impact of changing the neighborhood generation function for a local interpretable model-agnostic explanator by proposing four different variants. All the proposed methods are based on a grid-based segmentation of the images, but each of them proposes a different strategy for generating the neighborhood of the image for which an explanation is required. A deep experimentation shows both improvements and weakness of each proposed approach.
URLhttps://link.springer.com/chapter/10.1007/978-3-030-16148-4_5
DOI10.1007/978-3-030-16148-4_5
Research Project: