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

Source: [Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data](<https://www.sota2.com/research/paper/68fa5ef31e209131ce9e684a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:04:52.118Z

Authors: Ludwig Schallner, Johannes Rabold, Oliver Scholz, Ute Schmid

Published: 2019-10-17T12:30:05.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1910.07856>)

[PDF](<https://arxiv.org/pdf/1910.07856.pdf>)