基于解耦残差提示的零样本工业异常检测方法

doi:10.3969/j.issn.1000-1565.2026.05.004

河北大学学报(自然科学版) ›› 2026, Vol. 46 ›› Issue (5): 486-494.DOI: 10.3969/j.issn.1000-1565.2026.05.004

基于解耦残差提示的零样本工业异常检测方法

张佳林^1,2,李梓响^1,2,郑晨昱^1,2,杨琬琳^1,3,熊鹰^1,3

收稿日期:2026-04-01 出版日期:2026-09-25 发布日期:2026-09-15
通讯作者: 国家自然科学基金项目(62173260;62303358);湖北省自然科学基金项目(2024AFB641)
作者简介:张佳林(2000—),男,武汉科技大学在读硕士研究生,主要从事工业图像异常检测方向研究. E-mail:15712566756@163.com

Zero-shot industrial anomaly detection method based on decoupled residual prompts

ZHANG Jialin^1,2, LI Zixiang^1,2, ZHENG Chenyu^1,2, YANG Wanlin^1,3, XIONG Ying^1,3

1.Key Laboratory of Metallurgical Equipment and Control Technology, Ministry of Education, Wuhan University of Science and Technology, Wuhan 430081, China; 2.Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering, Wuhan University of Science and Technology, Wuhan 430081, China; 3.Precision Manufacturing Institute, Wuhan University of Science and Technology, Wuhan 430081, China

Received:2026-04-01 Online:2026-09-25 Published:2026-09-15

摘要/Abstract

摘要： 在多品种、小批量智能制造生产线中,工业异常样本稀缺且产品迭代速度快,传统有监督深度学习模型面临训练数据难以获取、换线部署周期长的问题. 针对该问题,本文提出一种基于视觉-语言大模型的解耦残差提示异常检测模型.该模型在语言端采用文本初始化残差提示学习,将专家语义描述转化为可计算的决策先验,再经深度连续提示微调,解耦全局与局部异常语义.视觉端设计V-V自注意力机制,用于增强局部特征内聚性,提升微小异常的定位能力. 在MVTec AD和VisA基准数据集上,零样本条件下该方法的图像级受试者工作特征曲线下面积(AUROC)分别为91.4%和83.8%,像素级AUROC分别为91.7%和96.0%,优于现有主流方法.

关键词: 工业异常检测, 零样本异常检测, 视觉-语言模型, 解耦残差提示, 局部特征增强

中图分类号:

TP391

张佳林, 李梓响, 郑晨昱, 杨琬琳, 熊鹰. 基于解耦残差提示的零样本工业异常检测方法[J]. 河北大学学报(自然科学版), 2026, 46(5): 486-494.

ZHANG Jialin, LI Zixiang, ZHENG Chenyu, YANG Wanlin, XIONG Ying. Zero-shot industrial anomaly detection method based on decoupled residual prompts[J]. Journal of Hebei University(Natural Science Edition), 2026, 46(5): 486-494.

参考文献

[1] 苏虎,张家斌,张博豪,等.基于视觉感知的表面缺陷检测综述[J].计算机集成制造系统, 2023, 29(1): 169-191. DOI: 10.13196/j.cims.2023.01.015.
[2] Li Z, Yan Y H, Wang X H, et al. A survey of deep learning for industrial visual anomaly detection[J]. Artif Intell Rev, 2025, 58(9): 279. DOI:10.1007/s10462-025-11287-7.
[3] Mao Y, Chen Z Y, Liu Y, et al. A survey on industrial image anomaly detection: methods, benchmarks and rethinks[J]. Measurement, 2025, 256: 118377. DOI:10.1016/j.measurement.2025.118377.
[4] Shukla V, Shukla A, Surya Prakash S K, et al. A systematic survey: role of deep learning-based image anomaly detection in industrial inspection contexts[J]. Front Robot AI, 2025, 12: 1554196. DOI:10.3389/frobt.2025.1554196.
[5] Saeed U, Jan S U, Ahmad J, et al. Generative adversarial networks-enabled anomaly detection systems: a survey[J]. Expert Syst Appl, 2026, 296: 128978. DOI:10.1016/j.eswa.2025.128978.
[6] Defard T, Setkov A, Loesch A, et al. PaDiM: a patch distribution modeling framework for anomaly detection and localization[C] //Pattern Recognition. ICPR International Workshops and Challenges. ACM, 2021: 475-489. DOI:10.1007/978-3-030-68799-1_35.
[7] Roth K, Pemula L, Zepeda J, et al. Towards total recall in industrial anomaly detection[C] //2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). June 18-24, 2022. New Orleans, LA, USA. IEEE, 2022: 14298-14308. DOI:10.1109/cvpr52688.2022.01392.
[8] Song S. Contrastive learning-based one-class classification for intelligent manufacturing system[J]. Machines, 2025, 13(12): 1109. DOI:10.3390/machines13121109.
[9] Paolini D, Dini P, Soldaini E, et al. One-class anomaly detection for industrial applications: a comparative survey and experimental study[J]. Computers, 2025, 14(7): 281. DOI:10.3390/computers14070281.
[10] Liznerski P, Ruff L, Vandermeulen R A, et al. Explainable deep one-class classification[PP/OL]. V3. arXiv(2021-03-18)[2026-03-25]. https://doi.org/10.48550/arXiv.2007.01760.
[11] Radford A, Kim J W, Hallacy C, et al. Learning transferable visual models from natural language supervision[C] //Proceedings of the 38th International Conference on Machine Learning. 2021, 139: 8748-8763.
[12] Li X F, Zhang Z Z, Tan X, et al. PromptAD: learning prompts with only normal samples for few-shot anomaly detection[C] //2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). June 16-22, 2024. Seattle, WA, USA. IEEE, 2024: 16848-16858. DOI:10.1109/cvpr52733.2024.01594.
[13] Chen X H, Zhang J N, Tian G Z, et al. CLIP-AD: a language-guided staged dual-path model for zero-shot anomaly detection[PP/OL]. V2. arXiv(2024-03-02)[2026-03-25]. https://doi.org/10.48550/arXiv.2311.00453.
[14] Zhou K Y, Yang J K, Loy C C, et al. Learning to prompt for vision-language models[J]. Int J Comput Vis, 2022, 130(9): 2337-2348. DOI:10.1007/s11263-022-01653-1.
[15] Zhou Q H, Pang G S, Tian Y, et al. AnomalyCLIP: object-agnostic prompt learning for zero-shot anomaly detection[C] //The Twelfth International Conference on Learning Representations. 2023.
[16] Cao Y K, Zhang J N, Frittoli L, et al. AdaCLIP: adapting CLIP with hybrid learnable prompts for zero-shot anomaly detection[C] //Computer Vision-ECCV 2024. ACM, 2024: 55-72. DOI:10.1007/978-3-031-72761-0_4.
[17] Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: transformers for image recognition at scale[C] //Proceedings of the 9th International Conference on Learning Representations(ICLR). 2021.
[18] Liu Z, Lin Y T, Cao Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C] //2021 IEEE/CVF International Conference on Computer Vision(ICCV). October 10-17, 2021, Montreal, QC, Canada. IEEE, 2021: 9992-10002. DOI:10.1109/ICCV48922.2021.00986.
[19] Wang W H, Xie E Z, Li X, et al. Pyramid vision transformer: a versatile backbone for dense prediction without convolutions[C] //2021 IEEE/CVF International Conference on Computer Vision(ICCV). October 10-17, 2021, Montreal, QC, Canada. IEEE, 2021: 548-558. DOI:10.1109/ICCV48922.2021.00061.
[20] Batzner K, Heckler L, König R. EfficientAD: accurate visual anomaly detection at millisecond-level latencies[C] //2024 IEEE/CVF Winter Conference on Applications of Computer Vision(WACV). January 3-8, 2024. Waikoloa, HI, USA. IEEE, 2024: 127-137. DOI:10.1109/wacv57701.2024.00020.

基于解耦残差提示的零样本工业异常检测方法

Zero-shot industrial anomaly detection method based on decoupled residual prompts

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	代昕, 牟世源, 陈新超, 刘洋, 王鑫杰, 李晏兴, 付晓, 沈维政, 戴百生. 基于RGB-D数据和关键点动态定位的侧卧奶牛呼吸频率检测方法[J]. 河北大学学报(自然科学版), 2026, 46(5): 449-461.
[2]	顾禄辉,姚瑶,李佳舟,邓依凡,彭英琦. 基于改进RTDETR算法的产后母牛与犊牛行为实时分类模型[J]. 河北大学学报(自然科学版), 2026, 46(3): 237-248.
[3]	牛鹤,刘一凡,柴文磊,冯凡,刘亿. 在跨域环境下基于用户意图的访问控制[J]. 河北大学学报(自然科学版), 2026, 46(3): 327-336.
[4]	何梦腾,潘浩文,邓洪兴,许兴时,宋怀波. 基于点云多尺度方向一致性的羊只体尺测量方法[J]. 河北大学学报(自然科学版), 2026, 46(2): 113-127.
[5]	尹宁,王小伟,魏鹏程,周九道,施琳长弘,廖勇. 基于改进时延神经网络的水轮机异常声纹检测算法[J]. 河北大学学报(自然科学版), 2026, 46(2): 215-224.
[6]	张峰,张涛,花强,董春茹,朱杰. 基于图神经网络和注意力的点击率预测模型[J]. 河北大学学报(自然科学版), 2026, 46(1): 93-103.
[7]	冯慧敏,吕巧莉,陈俊芬. 基于关系一致性的多分支对比学习算法[J]. 河北大学学报(自然科学版), 2026, 46(1): 104-112.
[8]	付豪,张振利,陈源. 改进UNet++模型的脑肿瘤图像分割算法[J]. 河北大学学报(自然科学版), 2025, 45(4): 398-407.
[9]	贾承富,孙晓川,贾敬好,陈伟彬,李莹琦. 基于并行Mamba的轻量化息肉图像分割[J]. 河北大学学报(自然科学版), 2025, 45(4): 408-418.
[10]	杨昆,齐晁仪,刘天军,艾尚璞,闫森广,刘秀玲,薛林雁. 针对X线图像超分辨率重建的轻量残差注意力网络[J]. 河北大学学报(自然科学版), 2025, 45(4): 419-430.
[11]	廖勇,朱俊豪. 人工智能辅助的深海运载器探测技术研究进展[J]. 河北大学学报(自然科学版), 2025, 45(3): 299-308.
[12]	柯淇晟,花强,张博. 基于改进YOLOv8的遥感图像目标检测[J]. 河北大学学报(自然科学版), 2025, 45(3): 309-316.
[13]	李仁正,高冠东,宋胜尊,肖珂. 基于改进的FGM-CM-BERT模型多模态情感分析方法[J]. 河北大学学报(自然科学版), 2025, 45(2): 192-203.
[14]	郑伟,吴禹波,冯晓萌,马泽鹏,宋铁锐. 基于改进CycleGAN的非配对CMR图像增强[J]. 河北大学学报(自然科学版), 2025, 45(2): 204-215.
[15]	徐建民,王铭宇. 基于内容偏好和情绪倾向的微博用户兴趣画像构建方法[J]. 河北大学学报(自然科学版), 2025, 45(1): 91-103.