Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data

October 17, 2019 ยท Declared Dead ยท ๐Ÿ› PKDD/ECML Workshops

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Ludwig Schallner, Johannes Rabold, Oliver Scholz, Ute Schmid arXiv ID 1910.07856 Category cs.LG: Machine Learning Cross-listed q-bio.QM, stat.ML Citations 25 Venue PKDD/ECML Workshops Last Checked 4 months ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted