2019
Conference article  Open Access

Investigating neighborhood generation methods for explanations of obscure image classifiers

Guidotti R., Monreale A., Cariaggi L.

Image Classification  Neighborhood Generation  Explainable AI 

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.

Source: PAKDD, pp. 55–68, Macau, 14-17/04/2019

Publisher: Springer, Berlin, DEU



Back to previous page
Projects (via OpenAIRE)

Track and Know
Big Data for Mobility Tracking Knowledge Extraction in Urban Areas

SoBigData
SoBigData Research Infrastructure


OpenAIRE
BibTeX entry
@inproceedings{oai:it.cnr:prodotti:417417,
	title = {Investigating neighborhood generation methods for explanations of obscure image classifiers},
	author = {Guidotti R. and Monreale A. and Cariaggi L.},
	publisher = {Springer, Berlin, DEU},
	doi = {10.1007/978-3-030-16148-4_5},
	booktitle = {PAKDD, pp. 55–68, Macau, 14-17/04/2019},
	year = {2019}
}