Filters








23,843 Hits in 4.5 sec

Deep Visual Anomaly detection with Negative Learning [article]

Jin-Ha Lee, Marcella Astrid, Muhammad Zaigham Zaheer, Seung-Ik Lee
2021 arXiv   pre-print
In this paper, we propose anomaly detection with negative learning (ADNL), which employs the negative learning concept for the enhancement of anomaly detection by utilizing a very small number of labeled  ...  In the field of anomaly detection, improvements in deep learning opened new prospects of exploration for the researchers whom tried to automate the labor-intensive features of data collection.  ...  Deep-cascade net [20] is also trained with normal data to learn the Gaussian model during the training and use this model for anomaly detection in each step of the deep network.  ... 
arXiv:2105.11058v1 fatcat:kf6jkl4owfaldlqaq4kzznsk3q

Self-Supervised Anomaly Detection: A Survey and Outlook [article]

Hadi Hojjati, Thi Kieu Khanh Ho, Narges Armanfard
2022 arXiv   pre-print
of deep learning models.  ...  Over the past few years, anomaly detection, a subfield of machine learning that is mainly concerned with the detection of rare events, witnessed an immense improvement following the unprecedented growth  ...  Going Beyond Visual Anomaly Detection Traditionally, self-supervised learning literature focused on visual representation learning.  ... 
arXiv:2205.05173v2 fatcat:es7dkinhvrf7bepowfbbnj4hz4

Anomaly detection of industrial control systems based on transfer learning

Weiping Wang, Zhaorong Wang, Zhanfan Zhou, Haixia Deng, Weiliang Zhao, Chunyang Wang, Yongzhen Guo
2021 Tsinghua Science and Technology  
Results show that the proposed method achieves a high score and solves the time problem associated with deep learning model training.  ...  Thus, the proposed model ensures the safety of ICSs and verifies the feasibility of transfer learning for ICS anomaly detection.  ...  Deep learning models are quite effective in the field of detecting industrial process anomalies. Almalawi et al.  ... 
doi:10.26599/tst.2020.9010041 fatcat:hubi5iob5nc55o4tmvcbhpysey

DeepTimeAnomalyViz: A Tool for Visualizing and Post-processing Deep Learning Anomaly Detection Results for Industrial Time-Series [article]

Błażej Leporowski, Casper Hansen, Alexandros Iosifidis
2021 arXiv   pre-print
Deep Learning offers a possibility to create anomaly detection methods that can aid in preventing malfunctions and increasing efficiency.  ...  We introduce the DeTAVIZ interface, which is a web browser based visualization tool for quick exploration and assessment of feasibility of DL based anomaly detection in a given problem.  ...  Deep Learning (DL) has the potential to aid a variety of manufacturing processes by improving the anomaly detection and prediction.  ... 
arXiv:2109.10082v1 fatcat:k676mxodejg4bobyn4n34fcmdi

Deep Contrastive One-Class Time Series Anomaly Detection [article]

Rui Wang, Chongwei Liu, Xudong Mou, Xiaohui Guo, Kai Gao, Pin Liu, Tianyu Wo, Xudong Liu
2022 arXiv   pre-print
The accumulation of time series data and the absence of labels make time-series Anomaly Detection (AD) a self-supervised deep learning task.  ...  This paper proposes a deep Contrastive One-Class Anomaly detection method of time series (COCA), which combines the normality assumptions of contrastive learning and one-class classification.  ...  For instance, Deep SVDD [13] realizes a deep one-class classification framework for anomaly detection with deep fea-tures or representations learned by a pre-trained autoencoder. [14] presents the two-stage  ... 
arXiv:2207.01472v1 fatcat:uaprwn4eaff35o7vefbtr4vjki

Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection [article]

Jianpeng Zhang, Yutong Xie, Guansong Pang, Zhibin Liao, Johan Verjans, Wenxin Li, Zongji Sun, Jian He, Yi Li, Chunhua Shen, Yong Xia
2020 arXiv   pre-print
the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.  ...  If the anomaly score produced by the anomaly detection module is large enough or the confidence score estimated by the confidence prediction module is small enough, we accept the input as an anomaly case  ...  Many research efforts have been devoted to transfer the advantages of deep learning to anomaly detection. Ruff et al.  ... 
arXiv:2003.12338v4 fatcat:7vd5gjpqcrhipiloar2mk76bve

An Attention-Based Network for Textured Surface Anomaly Detection

Gaokai Liu, Ning Yang, Lei Guo
2020 Applied Sciences  
detection rates in terms of TPR (True Positive Rate) and TNR (True Negative Rate).  ...  Textured surface anomaly detection is a significant task in industrial scenarios.  ...  Acknowledgments: We sincerely appreciate the contribution of the DAGM and GNSS institutions for the open dataset to promote the development of textured surface anomaly detection.  ... 
doi:10.3390/app10186215 fatcat:wptncsgd5ncvtov5xuvfro2i5u

Deep social force network for anomaly event detection

Xingming Yang, Zhiming Wang, Kewei Wu, Zhao Xie, Jinkui Hou
2021 IET Image Processing  
Anomaly event detection is vital in surveillance video analysis. However, how to learn the discriminative motion in the crowd scene is still not tackled.  ...  The deep social force coding is modelled with multiple features, in which each feature can describe specific anomaly motion.  ...  RELATED WORK Anomaly event detection The key to video anomaly detection is anomaly feature learning.  ... 
doi:10.1049/ipr2.12299 fatcat:swdktlrbtnad5dwib35v3sq7s4

Anomaly Detection-Based Unknown Face Presentation Attack Detection [article]

Yashasvi Baweja, Poojan Oza, Pramuditha Perera, Vishal M. Patel
2020 arXiv   pre-print
In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end.  ...  Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users.  ...  An end-to-end deep learning solution is presented for fPAD based on anomaly detection. 2.  ... 
arXiv:2007.05856v1 fatcat:737aaqtk25cwvg7fd3chgfs2dm

Deep Structured Cross-Modal Anomaly Detection [article]

Yuening Li, Ninghao Liu, Jundong Li, Mengnan Du, Xia Hu
2019 arXiv   pre-print
To this end, we propose a novel deep structured anomaly detection framework to identify the cross-modal anomalies embedded in the data.  ...  Anomaly detection is a fundamental problem in data mining field with many real-world applications.  ...  Finally, we will introduce how to perform cross-modal anomaly detection with the built deep learning model. A.  ... 
arXiv:1908.03848v1 fatcat:lh6u54buvfcidokxc4lvi6mcry

ABNORMAL EVENT DETECTION BY MACHINE VISION USING DEEP LEARNING

Akshara Alex, Ashi Sahu, Avni Tanwar, Nisha Rathi, Kavita Namdev
2020 International Journal of Engineering Applied Sciences and Technology  
This paper proposes an abnormal event detection system through surveillance camera using machine vision, in corporation with deep learning, which analyzes footages of crowded scenes and detects abnormal  ...  The proposed model mainly depicts how deep learning elevates the quality of machine vision in abnormal event.  ...  Training and Testing- The proposed model is loaded with lot of positive and negative videos with labels, the network can automatically learn to predict the location of the anomaly in the video.  ... 
doi:10.33564/ijeast.2020.v04i12.028 fatcat:2rvyjx65rnc2vem4cg5jjcttge

Evaluation of Point Pattern Features for Anomaly Detection of Defect within Random Finite Set Framework [article]

Ammar Mansoor Kamoona, Amirali Khodadadian Gostar, Alireza Bab-Hadiashar, Reza Hoseinnezhad
2021 arXiv   pre-print
Recently, optical defect detection has been investigated as an anomaly detection using different deep learning methods.  ...  Random finite set-based defect detection is compared with state-of-the-arts anomaly detection methods.  ...  [26] proposed an evaluation of different deep anomaly detection methods for defect detection.  ... 
arXiv:2102.01882v1 fatcat:clzwdvfpuvhndgkexorzrikn6u

Multi-modal Anomaly Detection by Using Audio and Visual Cues

Ata-Ur-Rehman, Hafiz Sami Ullah, Haroon Farooq, Muhammad Salman Khan, Tayyeb Mahmood, Hafiz Owais Ahmed Khan
2021 IEEE Access  
The proposed anomaly detection algorithm makes use of both visual and audio features to automatically detect anomalous activities in scenes.  ...  An anomaly inference is developed which is based on both visual and audio features.  ...  anomaly detection by using two different audio classifiers Video Audio-Visual Anomaly Detection Audio-Visual Anomaly Detection with Sequences deep learning based audio classifier [19] with SVM audio  ... 
doi:10.1109/access.2021.3059519 fatcat:no3rmwypyzhmhnekuw4e4txy6m

Viral Pneumonia Screening on Chest X-rays Using Confidence-Aware Anomaly Detection

Jianpeng Zhang, Yutong Xie, Guansong Pang, Zhibin Liao, Johan Verjans, Wenxing Li, Zongji Sun, Jian He, Yi Li, Chunhua Shen, Yong Xia
2020 IEEE Transactions on Medical Imaging  
We therefore propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.  ...  If the anomaly score produced by the anomaly detection module is large enough, or the confidence score estimated by the confidence prediction module is small enough, the input will be accepted as an anomaly  ...  Many research efforts have been devoted to transfer the advantages of deep learning to anomaly detection. Ruff et al.  ... 
doi:10.1109/tmi.2020.3040950 pmid:33245693 fatcat:srekctmos5c5bmvvfu2waacasi

A Weak Supervision Approach to Detecting Visual Anomalies for Automated Testing of Graphics Units [article]

Adi Szeskin, Lev Faivishevsky, Ashwin K Muppalla, Amitai Armon, Tom Hope
2021 arXiv   pre-print
We present a deep learning system for testing graphics units by detecting novel visual corruptions in videos.  ...  This is achieved by reproducing driver bugs that increase the probability of generating corruptions, and by making use of ideas and methods from the Multiple Instance Learning (MIL) setting.  ...  Our goal, based on the above training data with weak labels given for entire videos, is to learn to detect visual corruptions in new incoming segments at test time.  ... 
arXiv:1912.04138v2 fatcat:6xvloc3yzvhuzfc6e2hmjj347y
« Previous Showing results 1 — 15 out of 23,843 results