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

arXiv: https://arxiv.org/abs/1910.07856 · HTML: https://mlsanity.com/paper/1910.07856/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2019.

## Built on by (most cited first, 5 of 5)

- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [REVEL Framework to measure Local Linear Explanations for black-box models: Deep Learning Image Classification case of study](https://mlsanity.com/paper/2211.06154/) (2022)
- [X-SHIELD: Regularization for eXplainable Artificial Intelligence](https://mlsanity.com/paper/2404.02611/) (2024)
- [LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations](https://mlsanity.com/paper/2111.08094/) (2021)
- [MiMICRI: Towards Domain-centered Counterfactual Explanations of Cardiovascular Image Classification Models](https://mlsanity.com/paper/2404.16174/) (2024)

## Abstract (arXiv)

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.