원문정보
한국차세대컴퓨팅학회
한국차세대컴퓨팅학회 학술대회
The 7th International Conference on Next Generation Computing 2021
2021.11
pp.328-330
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
Probabilistic modeling of normal data is commonly used for anomaly detection. In this paper, we present a novel anomaly detection process using a score-based probabilistic generative model. Our method is based on the Langevin dynamics-based sampling methods, but we use a reverse trajectory of a standard score-based framework to compute anomaly scores. We validate our anomaly detection framework according to different one-class classification settings on the MNIST dataset.
목차
Abstract
I. INTRODUCTION
II. RELATED WORK
A. Generative Adversarial Networks (GAN)
B. Score-based generative models
III. METHOD
A. Score Matching with Langevin Dynamics (SMLD)
B. Anomlay detection with score-based modeling
IV. EXPERIMENT
V. CONCLUSION
ACKNOWLEDGMENT
REFERENCES
I. INTRODUCTION
II. RELATED WORK
A. Generative Adversarial Networks (GAN)
B. Score-based generative models
III. METHOD
A. Score Matching with Langevin Dynamics (SMLD)
B. Anomlay detection with score-based modeling
IV. EXPERIMENT
V. CONCLUSION
ACKNOWLEDGMENT
REFERENCES