CG-HAF: An Interpretable Global-Local Lesion-Burden Fusion Framework for Ordinal Acne Severity Grading in Agentic Skincare Support

2026-09-25

AI Summary

This study addresses the entanglement of global and local evidence and the lack of interpretability in acne grading by proposing a global-local fusion framework. Methodologically, structured lesion descriptors are extracted through independently trained classifiers and object detectors, enabling explicit decoupling of holistic probabilities from localized features. A lightweight, interpretable classification model is then constructed to achieve transparent grading, revealing the critical role of standard alignment in cross-dataset transfer. Experimental results demonstrate that the proposed framework significantly outperforms purely global baselines, with particularly pronounced performance gains on severe cases. Ultimately, this approach provides reliable support for non-diagnostic skincare decision-making.

Abstract

Ordinal acne severity grading requires distinguishing visually similar neighboring grades while jointly weighing holistic facial appearance and localized lesion burden - evidence that most existing approaches collapse into a single opaque representation. We introduce CG-HAF, a global-local fusion framework that instead keeps this evidence explicit: averaged holistic severity probabilities from independently trained classifiers are combined with structured lesion-burden descriptors from an object detector (lesion count, detection confidence, lesion area) into a compact representation, from which a lightweight, interpretable classifier produces the final grade. On a widely used benchmark, this fusion yields a clear, statistically supported improvement over global-evidence-only baselines, with the largest gains on the most severe cases. Testing on an independent dataset with a different grading standard shows that strong within-dataset performance does not transfer automatically, and a follow-up diagnostic attributes much of this gap to mismatched grading criteria rather than detection failure alone. These findings support interpretable global-local fusion as an effective strategy for ordinal acne grading while highlighting criterion alignment as key to cross-dataset portability, with a further illustration of how the resulting severity signal can support transparent, non-diagnostic decision-making in skincare applications.

Problem

• acne severity grading
• ordinal classification
• global-local fusion
• interpretability
• cross-dataset generalization

Innovation

• Global-Local Fusion
• Interpretable Framework
• Ordinal Acne Grading
• Lesion-Burden Descriptors
• Cross-dataset Portability