计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 241200124-6.doi: 10.11896/jsjkx.241200124

• 计算机图形学&多媒体 • 上一篇    下一篇

SAM-MR:基于SAM的混合区域匹配专家适配布匹检测算法

罗其锋1, 肖星1, 温焯飞1, 池明旻2, 彭博3   

  1. 1 南方电网广东中山供电局 广东 中山 528401
    2 复旦大学计算机科学技术学院 上海 200438
    3上海海洋大学信息学院 上海 201306
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 彭博(bpeng@shou.edu.cn)
  • 作者简介:13824776366@139.com
  • 基金资助:
    南方电网公司科技项目(032000KC23030007(GDKJXM20230265))

SAM-MR:SAM-based Mixed Region Matching Expert Adaptation Algorithm for FabricDetection

LUO Qifeng1, XIAO Xing1, WEN Chaofei1, CHI Mingmin2, PENG Bo3   

  1. 1 Zhongshan Power Supply Bureau,Guangdong Power Grid Co.,Ltd.,Zhongshan,Guangdong 528401,China
    2 School of Computer Science and Technology,Fudan University,Shanghai 200438,China
    3 College of Information,Shanghai Ocean University,Shanghai 201306,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    Science and Technology Project of China Southern Power Grid Company(032000KC23030007(GDKJXM20230265)).

PDF (PC)

12

摘要： 有监督异常检测因其精准的工业异常检测能力而广泛应用于布匹质量检测。现有的统一架构的异常检测方法,因其单一的特征适配能力,不能对多样化的,所以度较高的布匹瑕疵进行有效地区分,因此在布匹的多类别的异常检测中性能会显著下降。为此提出一种基于混合区域匹配专家适配方法(Mixture of Region Experts),通过Mixture of Adapter Experts模块来区别化不同类别的布匹瑕疵特征,使用Align and Differencing模块对齐模板图特征和瑕疵特征来进一步加强异常区域的划分,从而有效提高了模型分辨复杂多类型的布匹瑕疵的能力。同时,模型进一步集成成分检测任务,在完成瑕疵定位的基础上实现异常成分的语义识别。实验结果表明,SAM-MR在布匹纤维材质和缺陷检测任务上取得了优于现有方法的性能,定性、定量分析及消融实验验证了所提出方法在多任务预测中的有效性。

关键词: 有监督学习, 异常检测, 混合专家

Abstract: Supervised anomaly detection has been widely applied to fabric quality inspection due to its high precision in industrial scenarios.However,existing unified-architecture methods often suffer from limited feature adaptation capabilities,making it difficult to distinguish diverse and highly similar fabric defects.This paper proposes a novel approach based on a Mixture of Region Experts(SAM-MR),which introduces a Mixture of Adapter Experts module to differentiate between various types of fabric defects.Additionally,an Align and Differencing module is employed to align features between template and defect images,further enhancing the localization of anomalous regions.The model is also extended to incorporate component detection,enabling semantic recognition of defect-related components on top of defect localization.Experimental results demonstrate that SAM-MR outperforms existing methods on fabric defect datasets,and qualitative,quantitative,and ablation studies validate the effectiveness of the proposed approach in multi-task prediction.

Key words: Supervised learning, Anomaly detection, Mixture of experts

中图分类号: 

  • TP181
[1]KIRILLOV A,MINTU E,RAVI N,et al.Segment anything[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2023:3992-4003.
[2]CAO Y K,XU X H,ZHANG J N,et al.A Survey on VisualAnomaly Detection:Challenge,Approach,and Prospect [J].arXiv:2401.16402,2024.
[3]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation [C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:801-818.
[4]SAEED M,EBRAHIMPOUR R.Mixture of experts:a literature survey [J].Artificial Intelligence Review,2014,42:275-293.
[5]ZHOU Y Q,LEI T,LIU H X,et al.Mixture-of-experts with expert-choice routing [C]//Advances in Neural Information Processing Systems.2022:7103-7114.
[6]RÜCKLÉ A,GEIGLE G,GLOCKNER M,et al.AdapterDrop:On the efficiency of adapters in transformers [J].arXiv:2010.11918,2020.
[7]CHEN Z,DUAN Y,WANG W,et al.Vision transformer adapter for dense predictions [J].arXiv:2205.08534,2022.
[8]SUNG Y L,CHO J,BANSAL M.V-Adapter:Parameter-effi-cient transfer learning for vision-and-language tasks [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5227-5237.
[9]CHAN C J,PANG G K H.Fabric defect detection by Fourier analysis [J].IEEE Transactions on Industry Applications,2000,36(5):1267-1276.
[10]HAN Y J,YU H J.Fabric defect detection system using stacked convolutional denoising auto-encoder trained with synthetic defect data [J].Applied Sciences,2020,10(7):2511.
[11]GHOSH A,GUHA T,BHAR R B,et al.Pattern classification of fabric defects using support vector machines [J].International Journal of Clothing Science and Technology,2011,23(2/3):142-151.
[12]KATTENBORN T,LEITLOFF J,SCHIEFER F,et al.Review on Convolutional Neural Networks(CNN) in vegetation remote sensing [J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,173:24-49.
[13]HE K,GKIOXARI G,DOLL?R P,et al.Mask R-CNN [C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2961-2969.
[14]DAI J,LI Y,HE K,et al.R-FCN:Object detection via region-based fully convolutional networks [C]//Advances in Neural Information Processing Systems.2016.
[15]VILLA M,DARDENNE G,NASAN M,et al.FCN-based approach for the automatic segmentation of bone surfaces in ultrasound images [J].International Journal of Computer Assisted Radiology and Surgery,2018,13:1707-1716.
[16]JI S P,SHEN Y Y,LU M,et al.Building Instance Change Detection from Large-Scale Aerial Images using Convolutional Neural Networks and Simulated Samples [J].Remote Sensing,2019,11(11):1343.
[17]LIU R Y,KUFFER M,PERSELLO C.The Temporal Dynamics of Slums Employing a CNN-Based Change Detection Approach [J].Remote Sensing,2019,11:2844.
[18]NEMOTO K,HAMAGUCHI R,SATO M,et al.Buildingchange detection via a combination of CNNs using only RGB aerial imageries [C]//Proceedings of the SPIE.2017.
[19]SINDAGI V A,SRIVASTAVA S.Domain adaptation for automatic OLED panel defect detection using adaptive support vector data description [J].International Journal of Computer Vision,2017,122(2):193-211.
[20]QIU K,TIAN L,WANG P.An effective framework of automated visual surface defect detection for metal parts [J].IEEE Sensors Journal,2021,21(18):20412-20420.
[21]BHATTACHARYA G,MANDAL B,PUHAN N B.Interleaved deep artifacts aware attention mechanism for concrete structural defect classification [J].IEEE Transactions on Image Processing,2021,30:6957-6969.
[22]ZENG Z,LIU B,FU J,et al.Reference-based defect detection network [J].IEEE Transactions on Image Processing,2021,30:6637-6647.
[23]RAHUTOMO F,KITASUKA T,ARITSUGI M.Semantic cosine similarity [C]//The 7th International Student Conference on Advanced Science and Technology ICAST.2012.
[24]SINGH A,HU R,GOSWAMI V,et al.FLAVA:A foundational language and vision alignment model [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:15638-15650.
[25]LI X,ZHANG Z,TAN X,et al.PromptAD:Learning prompts with only normal samples for few-shot anomaly detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2024:16838-16848.
[26]JEONG J,ZOU Y,KIM T,et al.WinCLIP:Zero-/few-shot anomaly classification and segmentation [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2023:19606-19616.
[27]HANLEY J A,MCNEIL B J.The meaning and use of the area under a receiver operating characteristic(ROC) curve [J].Radiology,1982,143(1):29-36.
[28]FUJINO A,ISOZAKI H,SUZUKI J.Multi-label text categorization with model combination based on F1-score maximization [C]//Proceedings of the Third International Joint Conference on Natural Language Processing.2008.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发