mlsanityData to 7 Oct 2026

P-WAE: Generalized Patch-Wasserstein Autoencoder for Anomaly Screening

arXiv 2108.03815 ↗First posted 9 Aug 2021cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection plays a pivotal role in numerous real-world scenarios, such as industrial automation and manufacturing intelligence. Recently, variational inference-based anomaly analysis has attracted researchers' and developers' attention. It aims to model the defect-free distribution so that anomalies can be classified as out-of-distribution samples. Nevertheless, there are two disturbing factors that need us to prioritize: (i) the simplistic prior latent distribution inducing limited expressive capability; (ii) the strong probability distance notion results in collapsed features. In this paper, we propose a novel Patch-wise Wasserstein AutoEncoder (P-WAE) architecture to alleviate those challenges. In particular, a patch-wise variational inference model coupled with solving the jigsaw puzzle is designed, which is a simple yet effective way to increase the expressiveness of the latent manifold. This makes using the model on high-dimensional practical data possible. In addition, we leverage a weaker measure, sliced-Wasserstein distance, to achieve the equilibrium between the reconstruction fidelity and generalized representations. Comprehensive experiments, conducted on the MVTec AD dataset, demonstrate the superior performance of our proposed method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 62 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

24 of 62 references.

References · 24

  1. 2013Auto-Encoding Variational Bayescited by 3,980
  2. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  3. 2016Deep Variational Information Bottleneckcited by 915
  4. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2019On Variational Bounds of Mutual Informationcited by 550
  7. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  8. 2017Wasserstein Auto-Encoderscited by 371
  9. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  10. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  11. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  12. 2018Latent Space Autoregression for Novelty Detectioncited by 149
12 more
  1. 2018Efficient GAN-Based Anomaly Detectioncited by 122
  2. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 120
  3. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  4. 2019The HSIC Bottleneck: Deep Learning without Back-Propagationcited by 77
  5. 2018Learning Deep Features for One-Class Classificationcited by 76
  6. 2017Sliced Wasserstein Distance for Learning Gaussian Mixture Modelscited by 59
  7. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  8. 2021Contrastive Syn-to-Real Generalizationcited by 32
  9. 2020Real-World Anomaly Detection by using Digital Twin Systems and Weakly-Supervised Learningcited by 17
  10. 2019Attribute Restoration Framework for Anomaly Detectioncited by 16
  11. 2019Attention Guided Anomaly Localization in Imagescited by 9
  12. 2020Combining GANs and AutoEncoders for Efficient Anomaly Detectioncited by 8

Built on by

Not cited yet.