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
    97 Citations
    Adaptive Adversarial Latent Space for Novelty Detection
    • Highly Influenced
    • PDF
    Novelty Detection via Non-Adversarial Generative Network
    • 3
    • PDF
    Latent Regularized Generative Dual Adversarial Network For Abnormal Detection
    • Highly Influenced
    • PDF
    P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection
    • 3
    • Highly Influenced
    • PDF
    Unsupervised Novelty Detection in Video with Adversarial Autoencoder Based on Non-Euclidean Space
    • Jinyoung Kim, Sung-Bae Cho
    • Computer Science
    • 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)
    • 2019
    • 1
    • Highly Influenced
    • PDF
    G2D: Generate to Detect Anomaly
    • PDF
    Compact Surjective Encoding Autoencoder for Unsupervised Novelty Detection
    • Highly Influenced
    HRN: A Holistic Approach to One Class Learning
    • 1
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 31 REFERENCES
    Adversarially Learned One-Class Classifier for Novelty Detection
    • 207
    • PDF
    Deep Transfer Learning for Multiple Class Novelty Detection
    • 22
    • PDF
    Generative Adversarial Nets
    • 20,807
    • PDF
    Conditional Generative Adversarial Nets
    • 4,172
    • PDF
    Deep One-Class Classification
    • 282
    • Highly Influential
    • PDF
    C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition
    • Poojan Oza, V. Patel
    • Computer Science
    • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2019
    • 41
    • PDF
    One-Class Convolutional Neural Network
    • 45
    • PDF
    Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
    • 7,380
    • PDF