• DOI:10.1109/CVPR.2019.00301
Corpus ID: 84186723

OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations

@article{Perera2019OCGANON,
  title={OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations},
  author={Pramuditha Perera and Ramesh Nallapati and B. Xiang},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={2893-2901}
}

Pramuditha Perera, Ramesh Nallapati, B. Xiang

Published 2019

Computer Science

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

We present a novel model called OCGAN for the classical problem of one-class novelty detection, where, given a set of examples from a particular class, the goal is to determine if a query example is from the same class. [...] Key Method In order to accomplish this goal, firstly, we force the latent space to have bounded support by introducing a tanh activation in the encoder's output layer.Expand Abstract

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed