earticle

논문검색

Poster Session III

Anomaly detection with score-based generative modeling

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

저자정보

  • Jeong-Hyeon Moon Department of Artificial Intelligence Department of Artificial Intelligence Ajou University
  • Kyung-Ah Sohn Department of Artificial Intelligence Ajou University

0개의 논문이 장바구니에 담겼습니다.