Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Review
نویسندگان
چکیده
Anomaly detection has become an indispensable tool for modern society, applied in a wide range of applications, from detecting fraudulent transactions to malignant brain tumors. Over time, many anomaly techniques have been introduced. However, general, they all suffer the same problem: lack data that represents anomalous behaviour. As behaviour is usually costly (or dangerous) system, it difficult gather enough such This, turn, makes develop and evaluate techniques. Recently, generative adversarial networks (GANs) attracted much attention research, due their unique ability generate new data. In this paper, we present systematic review literature area, covering 128 papers. The goal paper analyze relation between types GANs, identify most common application domains GAN-assisted GAN-based detection, assemble information on datasets performance metrics used assess them. Our study helps researchers practitioners find suitable technique application. addition, research roadmap future studies area. summary, GANs are address problem insufficient amount behaviour, either through augmentation or representation learning. commonly GAN architectures DCGANs, standard cGANs. primary include medicine, surveillance intrusion detection.
منابع مشابه
Automatic Colorization of Grayscale Images Using Generative Adversarial Networks
Automatic colorization of gray scale images poses a unique challenge in Information Retrieval. The goal of this field is to colorize images which have lost some color channels (such as the RGB channels or the AB channels in the LAB color space) while only having the brightness channel available, which is usually the case in a vast array of old photos and portraits. Having the ability to coloriz...
متن کاملEvolutionary Generative Adversarial Networks
Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this paper, we propose a novel GAN framework called evolutionary generative adversarial networks (E-GAN) for stable GAN training and improved generative performa...
متن کاملUnsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging. Models are typically based on large amounts of data with annotated examples of known markers aiming at automating detection. High annotation effort and the limitation to a vocabulary of known markers limit the power of such approaches. Here, we perform unsupervised learning to...
متن کاملUnrolled Generative Adversarial Networks
We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator’s objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable a...
متن کاملAnnealed Generative Adversarial Networks
Generative Adversarial Networks (GANs) have recently emerged as powerful generative models. GANs are trained by an adversarial process between a generative network and a discriminative network. It is theoretically guaranteed that, in the nonparametric regime, by arriving at the unique saddle point of a minimax objective function, the generative network generates samples from the data distributi...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Access
سال: 2021
ISSN: ['2169-3536']
DOI: https://doi.org/10.1109/access.2021.3131949