MAOL：面向细粒度工业缺陷严重程度分级的形态感知序数学习
MAOL: Morphology-Aware Ordinal Learning for Fine-Grained Industrial Defect Severity Grading
- Hebei University of Technology（河北工业大学）
- Yingli Energy Development Co. Ltd（英利能源发展有限公司）
- Hunan University（湖南大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对工业缺陷分级的挑战，提出MAOL框架，通过形态感知序数学习提升鲁棒性，在挑战赛中表现优异且性能优于多种基线方法。
AI中文摘要：
细粒度缺陷严重程度分级对工业检测至关重要，但由于严重程度标签的序数性质、对形态相关线索的强依赖性，以及两阶段流程中干净标注实例与带噪预测实例之间存在的训练-测试差异，该任务仍具挑战性。我们提出MAOL，即面向细粒度工业缺陷严重程度分级的形态感知序数学习框架。MAOL将严重程度分级表述为实例级序数学习任务，融入显式形态特征以增强表示学习，引入类条件自适应序数阈值对缺陷特定分级边界进行建模，并通过定位扰动采用预测感知训练以提升对不完美预测实例的鲁棒性。在干净ROI与预测实例两种设置下开展的大量实验表明，MAOL的性能始终优于基于规则的方法、名义分类模型及现有序数基线，尤其在预测实例设置中表现突出。该方法在2026年高精度制造细粒度严重程度分级IDA挑战赛中排名第三。
英文摘要：
Fine-grained defect severity grading is essential for industrial inspection, yet remains challenging due to the ordinal nature of severity labels, the strong dependence on morphology-related cues, and the train-test discrepancy between clean annotated instances and noisy predicted instances in two-stage pipelines. We propose MAOL, a Morphology-Aware Ordinal Learning framework for fine-grained industrial defect severity grading. MAOL formulates severity grading as an instance-level ordinal learning task, incorporates explicit morphological features to enhance representation learning, introduces class-conditional adaptive ordinal thresholds to model defect-specific grading boundaries, and employs prediction-aware training via localization perturbation to improve robustness to imperfect predicted instances. Extensive experiments under both clean-ROI and predicted-instance settings demonstrate that MAOL consistently outperforms rule-based methods, nominal classification models, and existing ordinal baselines, especially in the predicted-instance setting. The proposed approach ranked third in the IDA 2026 Challenge on Fine-Grained Severity Grading for High-Precision Manufacturing.
