Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data
This is an incremental study for researchers in explainable AI, focusing on the impact of superpixel aggregation on explanation reliability in biological data.
The study investigated how different superpixel segmentation methods affect visual explanations generated by LIME for image classification, finding that relevance areas varied significantly, with Quick-Shift showing the least and Compact-Watershed the highest correspondence to human references.
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.