.png){kind=icon}
返回
Deep anomaly detection with self-supervised learning and adversarial training
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2021.108234.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep anomaly detection, which utilizes neural networks to discover anomalies, is a vital research topic in pattern recognition. With the burgeoning of inference mechanism, inference-based methods show the promising performance. However, inference-based methods have two limitations: (1) they use an adver-sarial training way to learn data features. Such training way fails to learn task-specific features which can be conducive to capture the difference between normal and anomaly data. (2) The structure of detection network cannot capture the marginal distributions of normal data and corresponding features, which in-fluences on the performance of anomaly detection. To overcome these limitations, this paper proposes a deep adversarial anomaly detection (DAAD) method. Specifically, an auxiliary task with self-supervised learning is first designed to learn task-specific features. Then a deep adversarial training (DAT) model is constructed to capture marginal distributions of normal data in different spaces. In addition, a majority voting strategy is applied to obtain reliable detection results. Experimental results on image and sequence datasets show that proposed method performs significantly better than many strong baselines. (c) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Deep anomaly detection
Self-supervised learning
Adversarial training
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Social network model for crowd anomaly detection and localization面向人群异常检测与定位的社交网络模型.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Video anomaly detection and localization using motion-field shape description and homogeneity testingPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏分享收藏Self-supervised deep reconstruction of mixed strip-shredded text documentsPATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Gaussian field consensus: A robust nonparametric matching method for outlier rejectionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A comparative evaluation of outlier detection algorithms: Experiments and analysesPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Online growing neural gas for anomaly detection in changing surveillance scenesPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容