SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

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 O

Read original source ↗ Open in workspace

recordType

paper

region

Global