<p>Ablation study results on MVTec AD dataset.</p>

In the process of intelligentization in modern manufacturing, especially in industrial fields such as automobile manufacturing, semiconductor production, and electronic product assembly, product quality control is crucial. Traditional defect detection methods face problems such as supervised learning methods relying on a large amount of labeled data, weak generalization ability, and high cost. In the process of intelligent manufacturing, industrial product quality control is a key link to ensure production safety and product consistency. Especially in typical industrial scenarios such as automobile manufacturing, semiconductor production, and electronic product assembly, traditional defect detection methods are difficult to meet the needs of actual production lines for high-precision and high-efficiency detection due to their reliance on a large amount of labeled data, weak generalization ability, and high cost. To solve the problem of defect detection in small and zero sample scenarios in these industries, improve detection sensitivity and localization accuracy, and enhance the model’s generalization ability to unknown defects, a unsupervised industrial image defect detection method based on autoencoder and Generative Adversarial Networks (GANs) is proposed. This study constructs an Multi-level Deep feature Adaptive fusion AutoEncoder (MDAAE) module, extracts multi-scale features through Pre-Trained Convolutional Neural Backbone Networks (PTCNBN), introduces Attention Mechanism (AM) to dynamically calculate feature weights, and achieves feature fusion and reconstruction. Meanwhile, the self-AM is fused to improve the GANs. The self-attention module efficiently captures long-range dependencies and generates an adversarial network training objective function to optimize the generator’s unsaturated loss. The results showed that the Area Under the Curve (AUC) of the Recall-Precision curve of the research method reached 93.6 ± 0.5%, and its F1-Score value exceeded 0.890 ± 0.003 in defect types such as scratches and dents. In practical applications, the inference time of the research method remained stable at 3.0 ± 0.2 GB of central processor memory, and the Fréchet Inception Distance (FID) value fully converged at the 2230th iteration, with a stable FID value of 3. The false alarm rate was only 8.6 ± 0.7% under strong light conditions. The proposed UIIDD method based on autoencoder and GANs had good robustness, generalization ability, reliability, and efficiency. This study effectively solves the problems of poor robustness, weak generalization ability, and high cost of traditional defect detection methods.在现代制造业智能化进程中，尤其是汽车制造、半导体生产、电子产品组装等工业领域，产品质量管控至关重要。传统缺陷检测方法面临诸多痛点：监督学习方法依赖大量标注数据、泛化能力薄弱且实施成本高昂。在智能制造流程中，工业产品质量管控是保障生产安全与产品一致性的关键环节。尤其在上述典型工业场景下，传统缺陷检测方法因依赖大量标注数据、泛化能力弱、成本高昂，难以满足实际生产线对高精度、高效率检测的需求。为解决这些行业中小样本与零样本场景下的缺陷检测难题，提升检测灵敏度与定位精度，增强模型对未知缺陷的泛化能力，本文提出了一种基于自编码器（AutoEncoder）与生成对抗网络（Generative Adversarial Networks, GANs）的无监督工业图像缺陷检测方法。本研究构建了多级深度特征自适应融合自编码器（Multi-level Deep feature Adaptive fusion AutoEncoder, MDAAE）模块，通过预训练卷积神经网络骨干网络（Pre-Trained Convolutional Neural Backbone Networks, PTCNBN）提取多尺度特征，引入注意力机制（Attention Mechanism, AM）动态计算特征权重，实现特征融合与重构。同时，融合自注意力模块（self-AM）以优化生成对抗网络：该模块可高效捕获长距离依赖关系，并生成对抗网络训练目标函数以优化生成器的非饱和损失。实验结果表明，所提方法的查全率-查准率曲线下面积（Area Under the Curve, AUC）可达93.6±0.5%，在划痕、凹痕等缺陷类型下的F1分数（F1-Score）超过0.890±0.003。在实际应用中，该方法的推理内存占用稳定维持在3.0±0.2GB中央处理器内存，弗雷歇初始距离（Fréchet Inception Distance, FID）在第2230次迭代时完全收敛，稳定值为3。在强光条件下，其误报率仅为8.6±0.7%。本文提出的基于自编码器与生成对抗网络的无监督工业图像缺陷检测方法具备良好的鲁棒性、泛化能力、可靠性与运行效率。本研究有效解决了传统缺陷检测方法鲁棒性差、泛化能力弱、成本高昂的痛点问题。