Corpus ID: 218763382

Unsupervised anomaly localization using VAE and beta-VAE

@article{Zhou2020UnsupervisedAL,
  title={Unsupervised anomaly localization using VAE and beta-VAE},
  author={Leixin Zhou and Wenxiang Deng and Xiaodong Wu},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.10686}
}
  • Leixin Zhou, Wenxiang Deng, Xiaodong Wu
  • Published 2020
  • Computer Science
  • ArXiv
  • Variational Auto-Encoders (VAEs) have shown great potential in the unsupervised learning of data distributions. An VAE trained on normal images is expected to only be able to reconstruct normal images, allowing the localization of anomalous pixels in an image via manipulating information within the VAE ELBO loss. The ELBO consists of KL divergence loss (image-wise) and reconstruction loss (pixel-wise). It is natural and straightforward to use the later as the predictor. However, usually local… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    Unsupervised Anomaly Localization using Variational Auto-Encoders

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

    VIEW 3 EXCERPTS

    Anomaly Machine Component Detection by Deep Generative Model with Unregularized Score

    VIEW 1 EXCERPT