FuDU：面向工业缺陷检测的流式主动学习模糊双维度不确定性框架
FuDU: A Fuzzy Dual-dimensional Uncertainty Framework for Streaming Active Learning in Industrial Defect Detection
- School of Artificial Intelligence, Hebei University of Technology（河北工业大学人工智能学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对工业缺陷检测中深度学习模型实时可靠性问题，提出FuDU框架的流式主动学习方法，融合双维度不确定性实现自适应采样，适配核燃料棒缺陷检测等任务。
AI中文摘要：
确保深度学习模型在实时工业缺陷检测中的可靠性对高风险质量检测至关重要。为挖掘连续工业媒体流中的不确定样本，从而提升检测系统的可靠性，本文提出一种基于模糊双维度不确定性（FuDU）框架的流式主动学习方法。具体而言，我们首先在骨干网络上设计基于原型的全局不确定性量化（PGUQ）模块，通过正常/缺陷特征原型评估图像级不确定性；随后将双熵缺陷不确定性评估器（DeUE）集成到检测头中，以量化框级不确定性；最后，通过将不确定性建模为系统误差，提出一种模糊双维度不确定性感知策略，利用模糊推理融合双维度不确定性，实现专家知识驱动的自适应采样决策。综合实验表明，FuDU高效且灵活，非常适用于核燃料棒缺陷检测等具有挑战性的工业检测任务，其代码公开于该网址。
英文摘要：
Ensuring the reliability of deep learning models in real-time industrial defect detection is critical for high-stakes quality inspection. To mine uncertain samples within continuous industrial media streams, thereby enhancing the reliability of the detection system, this paper proposes a streaming active learning method based on the Fuzzy Dual-dimensional Uncertainty (FuDU) framework. Specifically, we first design a Prototype-based Global Uncertainty Quantification (PGUQ) module on the backbone to evaluate image-level uncertainty via normal/defective feature prototypes. A Dual-entropy defect Uncertainty Evaluator (DeUE) is then integrated into the detection head to quantify box-level uncertainty. Finally, by modeling uncertainty as systematic error, we propose a fuzzy dual-dimensional uncertainty-aware strategy that leverages fuzzy inference to fuse dual-dimensional uncertainties, enabling expert knowledge-driven adaptive sampling decisions. Comprehensive experiments demonstrate that FuDU is efficient and flexible, making it well-suited for challenging industrial inspection tasks such as the detection of nuclear fuel rod defects. Our code is publicly available at: https://github.com/wangzhaoyang-508/FuDU.
