• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
Advanced Search
Fan Ye, Peng Shujuan, Liu Xin, Cui Zhen, Wang Nannan. Cross-Modal Anomaly Detection via Hierarchical Deep Networks and Bi-Quintuple Loss[J]. Journal of Computer Research and Development, 2022, 59(12): 2770-2780. DOI: 10.7544/issn1000-1239.20210729
Citation: Fan Ye, Peng Shujuan, Liu Xin, Cui Zhen, Wang Nannan. Cross-Modal Anomaly Detection via Hierarchical Deep Networks and Bi-Quintuple Loss[J]. Journal of Computer Research and Development, 2022, 59(12): 2770-2780. DOI: 10.7544/issn1000-1239.20210729

Cross-Modal Anomaly Detection via Hierarchical Deep Networks and Bi-Quintuple Loss

Funds: This work was supported by the Open Research Projects of Zhejiang Lab (2021KH0AB01), the National Natural Science Foundation of China (61673185, 61922066, 62072244), the Natural Science Foundation of Fujian Province (2020J01083, 2020J01084), and the Open Research Projects of Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education (JYB202102).
More Information
  • Published Date: November 30, 2022
  • Cross-modal anomaly detection in big data environment is a very valuable and challenging work. Existing cross-modal anomaly detection framework often suffers from the incomplete data anomaly detection and low data utilization problems. To alleviate these concerns, an efficient cross-modal anomaly detection framework is proposed via hierarchical deep networks and similarity based bi-quintuple loss. First, the proposed framework introduces a single-view anomaly detection network to detect the attribute anomaly and part of class-attribute anomaly in data samples. Then, the similarity bi-quintuple loss, integrated with double-branch deep networks, is efficiently developed to detect the class anomaly and the remaining part class-attribute anomaly in data samples. Meanwhile, this loss regularizes the different attribute data with orthogonal property, and ensures the linear correlation between the same attribute data, enlarges the feature difference between different attribute data and increases the feature correlation between the same attribute data. Meanwhile, the bidirectional constraint and neighborhood constraint can significantly improve the data utilization and the generalization ability of the model. Extensive experimental results show that the proposed framework is able to detect possible abnormal sample points in different modalities, and outperforms the state-of-the-art corresponding methods, with obvious advantages.
  • Related Articles

    [1]Li Song, Cao Wenqi, Hao Xiaohong, Zhang Liping, Hao Zhongxiao. Collective Spatial Keyword Query Based on Time-Distance Constrained and Cost Aware[J]. Journal of Computer Research and Development, 2025, 62(3): 808-819. DOI: 10.7544/issn1000-1239.202330815
    [2]Liu Leyuan, Dai Yurou, Cao Yanan, Zhou Fan. Survey of User Geographic Location Prediction Based on Online Social Network[J]. Journal of Computer Research and Development, 2024, 61(2): 385-412. DOI: 10.7544/issn1000-1239.202220417
    [3]Zong Ming, Wang Xiaodong, and Zhou Xingming. Cost-Optimizing Adaptive Location Service Protocol in MANET[J]. Journal of Computer Research and Development, 2012, 49(12): 2515-2528.
    [4]Zheng Mingcai, Zhang Dafang, Luo Jian, Li Wenwei. Adaptive Controlling Mechanism for Data Duplicates Based on Prediction in WSN[J]. Journal of Computer Research and Development, 2011, 48(2): 296-305.
    [5]Yao Guohui, Zhu Daming, and Ma Shaohan. Approximating the Directed Minimum Degree Spanning Tree of Directed Acyclic Graph[J]. Journal of Computer Research and Development, 2009, 46(6): 1052-1057.
    [6]Xiao Fangxiong, Huang Zhiqiu, Cao Zining, Yuan Min, and Zhang Junhua. Describing and Cost Analyzing of Web Services Composition Using PPA[J]. Journal of Computer Research and Development, 2009, 46(5): 832-840.
    [7]Li Miqing, Zheng Jinhua, and Luo Biao. A Multi-Objective Evolutionary Algorithm Based on Minimum Spanning Tree[J]. Journal of Computer Research and Development, 2009, 46(5): 803-813.
    [8]Hu Caiping and Qin Xiaolin. Spatial Classification and Prediction Based on Fuzzy cmeans[J]. Journal of Computer Research and Development, 2008, 45(7): 1183-1188.
    [9]Qian Jiangbo, Xu Hongbing, Dong Yisheng, Wang Yongli, Liu Xuejun, Yang Xuemei. A Window Join Optimization Algorithm Based on Minimum Spanning Tree[J]. Journal of Computer Research and Development, 2007, 44(6): 1000-1007.
    [10]He Xiaoyang and Wang Yasha. Model-Based Methods for Software Cost Estimation[J]. Journal of Computer Research and Development, 2006, 43(5): 777-783.
  • Cited by

    Periodical cited type(13)

    1. 张鑫,张晗,牛曼宇,姬莉霞. 计算机视觉领域对抗样本检测综述. 计算机科学. 2025(01): 345-361 .
    2. 张少杰,赵李强,周静波,陈国坤,焦宗寒,杨伟,王欣,刘荣海. 电力行业无人机巡检可见光图像与激光点云数据配准方法研究. 云南电力技术. 2024(02): 70-73+80 .
    3. 顾芳铭,况博裕,许亚倩,付安民. 面向自动驾驶感知系统的对抗样本攻击研究综述. 信息安全研究. 2024(09): 786-794 .
    4. 武阳,刘靖. 面向图像分析领域的黑盒对抗攻击技术综述. 计算机学报. 2024(05): 1138-1178 .
    5. 郭凯威,杨奎武,张万里,胡学先,刘文钊. 面向文本识别的对抗样本攻击综述. 中国图象图形学报. 2024(09): 2672-2691 .
    6. 徐宇晖,潘志松,徐堃. 面向三种形态图像的对抗攻击研究综述. 计算机科学与探索. 2024(12): 3080-3099 .
    7. 秦书晨,王娟,朱倪宏,陈杨. 图像对抗样本检测与防御方法研究进展. 智能安全. 2024(04): 81-95 .
    8. 罗鑫,夏学知. 面向图像识别的对抗样本与攻击研究. 舰船电子工程. 2023(02): 22-29+33 .
    9. 杨宏宇,杨帆. 基于图像去噪和图像生成的对抗样本检测方法. 湖南大学学报(自然科学版). 2023(08): 72-81 .
    10. 张万里,陈越,杨奎武,张田,胡学先. 一种局部遮挡人脸识别的对抗样本生成方法. 计算机研究与发展. 2023(09): 2067-2079 . 本站查看
    11. 刘瑞祺,李虎,王东霞,赵重阳,李博宇. 图像对抗样本防御技术研究综述. 计算机科学与探索. 2023(12): 2827-2839 .
    12. 梁杰,彭长根,谭伟杰,何兴. 基于梯度惩罚WGAN的人脸对抗样本生成方法. 计算机与数字工程. 2023(11): 2659-2665 .
    13. 李前,蔺琛皓,杨雨龙,沈超,方黎明. 云边端全场景下深度学习模型对抗攻击和防御. 计算机研究与发展. 2022(10): 2109-2129 . 本站查看

    Other cited types(17)

Catalog

    Article views (182) PDF downloads (93) Cited by(30)

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return