AnoDFDNet: A Deep Feature Difference Network for Anomaly Detection

Author:

Wang Zhixue1ORCID,Zhang Yu1ORCID,Luo Lin1ORCID,Wang Nan1ORCID

Affiliation:

1. School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, China

Abstract

This paper proposed a novel anomaly detection (AD) approach of high-speed train images based on convolutional neural networks and the Vision Transformer. Different from previous AD works, in which anomalies are identified with a single image using classification, segmentation, or object detection methods, the proposed method detects abnormal difference between two images taken at different times of the same region. In other words, we cast anomaly detection problem with a single image into a difference detection problem with two images. The core idea of the proposed method is that the “anomaly” commonly represents an abnormal state instead of a specific object, and this state should be identified by a pair of images. In addition, we introduced a deep feature difference AD network (AnoDFDNet) which sufficiently explored the potential of the Vision Transformer and convolutional neural networks. To verify the effectiveness of the proposed AnoDFDNet, we gathered three datasets, a difference dataset (Diff dataset), a foreign body dataset (FB dataset), and an oil leakage dataset (OL dataset). Experimental results on the above datasets demonstrate the superiority of the proposed method. In terms of the F1-score, the AnoDFDNet obtained 76.24%, 81.04%, and 83.92% on Diff dataset, FB dataset, and OL dataset, respectively.

Funder

Science and Technology Program of Sichuan

Publisher

Hindawi Limited

Subject

Electrical and Electronic Engineering,Instrumentation,Control and Systems Engineering

Reference41 articles.

1. Deep learning for anomaly detection: a survey;C. Raghavendra,2019

2. Deep Learning for Anomaly Detection

3. A Unifying Review of Deep and Shallow Anomaly Detection

4. Fraud detection system: A survey

5. Real-time illegal parking detection system based on deep learning;X. M. Xie

Cited by 12 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization;Sensors;2024-02-20

2. Exploring Convolution Neural Networks for Image Classification in Medical Imaging;2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE);2024-01-24

3. Real-Time Object Detection on Edge Devices Using Mobile Neural Networks;2024 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE);2024-01-24

4. Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open- Access Papers;Applied System Innovation;2024-01-22

5. Change Detection in Pipe Image Pairs Extracted from Inspection Videos by Sequential Filtering;2024 IEEE/SICE International Symposium on System Integration (SII);2024-01-08

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3