Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Effect of superpixel aggregation on explanations in LIME - A case study with biological data

: Schallner, L.; Rabold, J.; Scholz, O.; Schmid, U.


Cellier, P.:
Machine Learning and Knowledge Discovery in Databases. Proceedings. Pt.I : International Workshops of ECML PKDD 2019, Würzburg, Germany, September 16-20, 2019
Cham: Springer Nature, 2020 (Communications in computer and information science 1167)
ISBN: 978-3-030-43822-7 (Print)
ISBN: 978-3-030-43823-4 (Online)
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) <2019, Würzburg>
Conference Paper
Fraunhofer IIS ()

End-to-end learning with deep neural networks, such as convolutional neural networks (CNNs), has been demonstrated to be very successful for different tasks of image classification. To make decisions of black-box approaches transparent, different solutions have been proposed. LIME is an approach to explainable AI relying on segmenting images into superpixels based on the Quick-Shift algorithm. In this paper, we present an explorative study of how different superpixel methods, namely Felzenszwalb, SLIC and Compact-Watershed, impact the generated visual explanations. We compare the resulting relevance areas with the image parts marked by a human reference. Results show that image parts selected as relevant strongly vary depending on the applied method. Quick-Shift resulted in the least and Compact-Watershed in the highest correspondence with the reference relevance areas.