# When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations

arXiv: https://arxiv.org/abs/2609.07462 · HTML: https://mlsanity.com/paper/2609.07462/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval](https://mlsanity.com/paper/1502.07058/) (2015)
- [PaddleOCR 3.0 Technical Report](https://mlsanity.com/paper/2507.05595/) (2025)
- [S-LIME: Stabilized-LIME for Model Explanation](https://mlsanity.com/paper/2106.07875/) (2021)
- [BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations](https://mlsanity.com/paper/2012.03058/) (2020)
- [Statistical stability indices for LIME: obtaining reliable explanations for Machine Learning models](https://mlsanity.com/paper/2001.11757/) (2020)
- [To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods](https://mlsanity.com/paper/2106.00461/) (2021)
- [An Analysis of LIME for Text Data](https://mlsanity.com/paper/2010.12487/) (2020)
- [Looking Deeper into Tabular LIME](https://mlsanity.com/paper/2008.11092/) (2020)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [Which LIME should I trust? Concepts, Challenges, and Solutions](https://mlsanity.com/paper/2503.24365/) (2025)
- [On Evaluation of Document Classification using RVL-CDIP](https://mlsanity.com/paper/2306.12550/) (2023)
- [DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification](https://mlsanity.com/paper/2407.03830/) (2024)
- [Segmentation and Smoothing Affect Explanation Quality More Than the Choice of Perturbation-based XAI Method for Image Explanations](https://mlsanity.com/paper/2409.04116/) (2024)

## Abstract (arXiv)

Post-hoc explanation methods are widely used to inspect image classifiers, but their reliability depends on design choices that are often treated as implementation details. We study this issue for LIME on document image classification, focusing on the segmentation step that defines the interpretable units being perturbed. Standard image-based LIME typically relies on natural-image superpixels, which are poorly aligned with document structure such as text regions, layout blocks, and identification codes. Using RVL-CDIP, we compare Quickshift and SLIC with document-aware segmentations based on OCR bounding boxes and regular grids. Our results show that segmentation strongly affects explanation consistency, correctness, and local fidelity. Document-aware segmentations produce more stable and faithful explanations, require fewer perturbations to converge, and expose shortcut behaviour based on document identification codes, a known RVL-CDIP bias that superpixel-based LIME often obscures. These findings show that reliable post-hoc explanation requires domain-aware interpretable representations, and that segmentation should be treated as part of the explanation method rather than as neutral preprocessing.