Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection

@article{Gong2019MemorizingNT,
  title={Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection},
  author={Dong Gong and L. Liu and Vuong Le and Budhaditya Saha and M. Mansour and S. Venkatesh and A. V. D. Hengel},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={1705-1714}
}
  • Dong Gong, L. Liu, +4 authors A. V. D. Hengel
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Deep autoencoder has been extensively used for anomaly detection. [...] Key Result Experiments on various datasets prove the excellent generalization and high effectiveness of the proposed MemAE.Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 36 CITATIONS

    Learning Memory-guided Normality for Anomaly Detection

    VIEW 13 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Memory Augmented Generative Adversarial Networks for Anomaly Detection

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Inverse-Transform AutoEncoder for Anomaly Detection

    VIEW 3 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Neural Memory Plasticity for Anomaly Detection

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Neural memory plasticity for medical anomaly detection

    FILTER CITATIONS BY YEAR

    2019
    2020

    CITATION STATISTICS

    • 5 Highly Influenced Citations

    • Averaged 18 Citations per year from 2019 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 57 REFERENCES

    Spatio-Temporal AutoEncoder for Video Anomaly Detection

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep One-Class Classification

    VIEW 1 EXCERPT

    Deep Structured Energy Based Models for Anomaly Detection

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Latent Space Autoregression for Novelty Detection

    Adversarially Learned One-Class Classifier for Novelty Detection

    VIEW 3 EXCERPTS

    A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning to Generate with Memory

    VIEW 1 EXCERPT