cs.LGNov 19, 2026

Class-Conditional Conformal Triage for ICAO Face-Image Compliance under Class Imbalance

Authors: Mustafa Vedat Yildirim, Inna Skarga-Bandurova

Organizations: School of Engineering, Computing and Mathematics, Oxford Brookes University, Headington Road, Oxford OX3 0BP, United Kingdom

Abstract

Automated ICAO/ISO face-image compliance analysers provide criterion-level pass/fail decisions, yet these verdicts do not quantify uncertainty when deciding whether to accept, reject, or retake a photograph. We investigate conformal prediction as a triage layer for BioGaze, evaluating 14 compliance criteria on the synthetic TONO benchmark. Without retraining the analyser, we fit per-criterion logistic classifiers and compare marginal and label-conditional (Mondrian) conformal prediction with conventional abstention rules using subject-disjoint splits. Marginal conformal prediction achieved approximately 0.90 overall coverage but substantially under-covered violations, with a ten-partition mean of 0.37 for one criterion. The corresponding Mondrian means ranged from 0.89 to 0.92 across criteria. However, most of the reduction in criterion-level false positives came from the logistic layer (0.145 to 0.048), while tuned abstention rules achieved lower false-positive rates than Mondrian at comparable retake rates. Bonferroni correction for joint coverage across 14 criteria required retaking nearly all images. These findings show that class-conditional conformal prediction can achieve near-target empirical coverage for minority violation classes and reveal trade-offs between statistical coverage, classification performance, and retake requirements in multi-criterion face-image compliance assessment.

Explore similar work

CardsList
  1. A Quiet Failure in Calibrated Virtual Screening: Marginal Conformal Prediction Under-Covers the Minority Class, and a Class-Conditional Fix Recovers It

    Jul 7, 2026Muhammadjon Tursunbadalov, Mustafojon TursunbadalovClass-Imbalanced LearningConformal Prediction

  2. Predicted Class Correction: Conformal Thresholds for Classes with No Calibration Data

    Oct 18, 2026One Octadion, Novanto Yudistira, Yuta NakashimaConformal PredictionGroup-Conditional Conformal Prediction

  3. Certify, Report, or Refuse: Harm-Constrained Conformal Prediction for Clinical Actions

    Nov 9, 2026Zhiyuan Li, Lequan YuConformal PredictionConformal Risk Control