发表机构
National Technical University of Athens; German Aerospace Center (DLR); Philips; University of Bonn（雅典国立技术大学; 德国航空航天中心; 飞利浦; 波恩大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对制造业数据稀缺导致的视觉检测可信性不足问题，该研究结合扩散模型生成合成缺陷样本与贝叶斯分类器的不确定性感知决策，构建分阶段流水线，初步结果显示可降低部署可信检测模型的成本。
AI 中文摘要
制造业中的自动化视觉检测旨在替代缓慢且不一致的人工检查，但其经济价值取决于其决策是否足够可信，以实现常规检测的自动化，同时将专业人力保留用于处理模糊案例。在生产线场景中，缺陷样本稀缺，因为生产过程经过优化以产出合格部件，这限制了仅基于真实数据训练的任何基于学习的检测器的性能。此外，以无置信度估计的硬标签形式输出的缺陷决策会产生不对称成本：误拒收会浪费合格产品，而误接收则可能增加未被检测到的缺陷在生产流程中扩散的风险。我们通过扩散模型生成合成缺陷样本以缓解数据稀缺问题，并采用贝叶斯分类器满足对置信度感知决策的需求，该分类器会将模糊单元弃权（不执行），而非对其进行错误分类。这些组件被嵌入到由连续、互补检查组成的分阶段流水线中。我们在真实缺陷的测试集上评估合成数据增强对分类和定位的影响，并从决策、合成数据和流水线结构三个方面检验系统的可信性。这项正在进行的工作报告了初步结果，表明在数据稀缺场景下，扩散生成的缺陷与不确定性感知分类相结合，可降低构建可信、可部署检测模型的成本。
英文摘要
Automated visual inspection in manufacturing aims to replace slow and inconsistent manual checks, but its economic value depends on whether its decisions can be trusted enough to automate routine inspection while reserving human expertise for ambiguous cases. In production-line settings, defective samples are scarce, since the process is optimized to produce good parts, which limits any learning-based inspector trained on real data alone. Compounding this, defect decisions emitted as hard labels with no confidence estimate carry an asymmetric cost: a false reject wastes a good product, while a false accept may increase the risk of undetected defects progressing through the production process. We address both problems by mitigating data scarcity through the generation of synthetic defective samples with a diffusion model, and meeting the need for confidence-aware decisions with a Bayesian classifier that defers ambiguous units to human review rather than misclassifying them. These components are embedded in a staged pipeline of successive, complementary checks. We evaluate how synthetic augmentation affects classification and localization on a test set of real defects, and examine the system's trustworthiness at three points: the decision, the synthetic data, and the pipeline structure. This work-in-progress reports preliminary results suggesting that diffusion-generated defects, combined with uncertainty-aware classification, can lower the cost of reaching a trustworthy, deployable inspection model under data scarcity.
CommentsAccepted at International Conference on the Economics of Grids, Clouds, Systems, and Services (GECON) 2026
