cs.AINov 7, 2026

Evaluating classification and explainability in multimodal petrographic image analysis

Authors: Thomas James Wood, Oktay Karakuş, Can Eyüpoğlu

Organizations: Department of Earth and Environmental Sciences, Cardiff University, Cardiff, United Kingdom. · Department of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom. · Department of Computer Engineering, Turkish Air Force Academy, National Defence University, Istanbul, Türkiye.

Abstract

Automated thin-section classifiers increasingly combine plane-polarised and cross-polarised light (PPL and XPL), two complementary views central to petrographic identification. Classification accuracy alone does not reveal whether model errors reflect mineralogical relationships, how predictions depend on each optical view, or whether attribution maps identify regions that influence model decisions. Here, we examine these complementary aspects of the released LITHOS dual-stream vision transformer using outputs from an earlier evaluation of 105,802 expert-annotated grains across 25 categories. Classification errors frequently followed the label taxonomy: 72.6% of misclassified plagioclase, microcline and sanidine grains were assigned the generic Feldspar label, while 87.1% of quartz-family grains received a label within that family, compared with 66.6% assigned their exact label. Replacing the XPL input with its per-channel spatial means produced a greater reduction in true-class probability than equivalent PPL replacement in 20 of 25 categories, but not in the three quartz categories. Five explainable artificial intelligence (XAI) attribution procedures generated visually distinct maps for identical inputs. In a superpixel-deletion analysis involving 30 grains from 29 thin sections, method-minus-random contrasts ranged from −0.043-0.043 to 0.0570.057, with all 41 simultaneous 95% confidence intervals including zero. Together, these findings show that error structure, modality sensitivity and attribution behaviour capture distinct aspects of model performance that cannot be established from classification accuracy or visual inspection of attribution maps alone.

Figures & tables

Explore similar work

CardsList
  1. Cross-polarization pairing for label-free few-shot thin-section classification

    Oct 17, 2026Bingchen YanFew-Shot Image ClassificationMicroscopy Image Analysis

  2. From Boundaries to Semantics: Prompt-Guided Multi-Task Learning for Petrographic Thin-section Segmentation

    Apr 16, 2026Yili Ren, Shiqi Wen, Li Hou +8Image SegmentationPromptable Image Segmentation

  3. Reconstructed holograms and explanation-aware evaluation for low-cost computational pollen analysis in veterinary cytology

    Sep 19, 2026Swarn Warshaneyan, Joial Danyal, Blaž Cugmas +4Microscopy Image AnalysisExplainable Image Classification