https://scholars.lib.ntu.edu.tw/handle/123456789/581299
標題: | One-class anomaly detection via novelty normalization | 作者: | Wu J.-C Lu S Fuh C.-S Liu T.-L. CHIOU-SHANN FUH |
關鍵字: | Classification (of information); Image enhancement; Security of data; Accuracy and precision; Auto encoders; Cyber security; Real-world; Reconstruction error; State of the art; Steep drop; Training procedures; Anomaly detection | 公開日期: | 2021 | 卷: | 210 | 來源出版物: | Computer Vision and Image Understanding | 摘要: | Anomaly detection is an important task in many real-world applications, such as within cybersecurity and surveillance. As with most data these days, the size and dimensionality of the data within these fields are constantly growing, which makes it essential to develop an approach that can both accurately and efficiently identify anomalies within these datasets. In this paper, we address the problem of one-class anomaly detection, where after training on a singular class, we try to determine whether or not inputs belong to that said class. Most of the currently existing methods have limitations in which the criterion of the novel class relies solely on the reconstruction error term. We attempt to break away from this restriction by proposing the use of an autoencoder network with a normalization term. We pair this with an additive novelty scoring module during the training procedure as a way to determine the difference between a given image and our determined normal class, therefore improving the efficiency of our model. We evaluate our model on MNIST, CIFAR-10, and Fashion-MNIST, three popular datasets for image classification, and compare the results against other various state-of-the-art models to determine the efficacy of our efforts. Our model not only outperforms the existing methods, but it also gives us a narrower range of AUCs for the tested classes, suggesting a stark improvement in both accuracy and precision. Moreover, we discover that introducing this “Novelty Normalization” concept into our model allows us to expand its usage into multiclass scenarios without a steep drop in accuracy. ? 2021 Elsevier Inc. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107693088&doi=10.1016%2fj.cviu.2021.103226&partnerID=40&md5=0b859e6b474f20fabffb2c24ea74512f https://scholars.lib.ntu.edu.tw/handle/123456789/581299 |
ISSN: | 10773142 | DOI: | 10.1016/j.cviu.2021.103226 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。