Investigating Neighborhood Generation Methods for Explanations of Obscure Image Classifiers


== Abstract ==

Given 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.


== Original document ==

The different versions of the original document can be found in:

* [http://dx.doi.org/10.1007/978-3-030-16148-4_5 http://dx.doi.org/10.1007/978-3-030-16148-4_5] under the license http://www.springer.com/tdm

* [http://hdl.handle.net/11568/1023226 http://hdl.handle.net/11568/1023226]

* [https://publications.cnr.it/doc/417417 https://publications.cnr.it/doc/417417]

* [http://link.springer.com/content/pdf/10.1007/978-3-030-16148-4_5 http://link.springer.com/content/pdf/10.1007/978-3-030-16148-4_5],
: [http://dx.doi.org/10.1007/978-3-030-16148-4_5 http://dx.doi.org/10.1007/978-3-030-16148-4_5] under the license http://www.springer.com/tdm

* [https://dblp.uni-trier.de/db/conf/pakdd/pakdd2019-1.html#GuidottiMC19 https://dblp.uni-trier.de/db/conf/pakdd/pakdd2019-1.html#GuidottiMC19],
: [https://link.springer.com/chapter/10.1007/978-3-030-16148-4_5 https://link.springer.com/chapter/10.1007/978-3-030-16148-4_5],
: [https://rd.springer.com/chapter/10.1007/978-3-030-16148-4_5 https://rd.springer.com/chapter/10.1007/978-3-030-16148-4_5],
: [https://academic.microsoft.com/#/detail/2934229219 https://academic.microsoft.com/#/detail/2934229219]