Deep One-Class Classification

Explore this paper's citation graph

Summary

This paper introduces a new anomaly detection method—Deep Support Vector Data Description—, which is trained on an anomaly detection based objective and shows the effectiveness of the method on MNIST and CIFAR-10 image benchmark datasets as well as on the detection of adversarial examples of GT-SRB stop signs.

Type
article
Published
2018-07-03
Cited by
2,784
References
59

Keywords

Class (philosophy), Artificial intelligence, Computer science

References

Cited by

Related papers