mlsanityData to 7 Oct 2026

Unsupervised Two-Stage Anomaly Detection

arXiv 2103.11671 ↗First posted 22 Mar 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Anomaly detection from a single image is challenging since anomaly data is always rare and can be with highly unpredictable types. With only anomaly-free data available, most existing methods train an AutoEncoder to reconstruct the input image and find the difference between the input and output to identify the anomalous region. However, such methods face a potential problem - a coarse reconstruction generates extra image differences while a high-fidelity one may draw in the anomaly. In this paper, we solve this contradiction by proposing a two-stage approach, which generates high-fidelity yet anomaly-free reconstructions. Our Unsupervised Two-stage Anomaly Detection (UTAD) relies on two technical components, namely the Impression Extractor (IE-Net) and the Expert-Net. The IE-Net and Expert-Net accomplish the two-stage anomaly-free image reconstruction task while they also generate intuitive intermediate results, making the whole UTAD interpretable. Extensive experiments show that our method outperforms state-of-the-arts on four anomaly detection datasets with different types of real-world objects and textures.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 22 Mar 2021.

Builds on

39 of 52 references.

References · 39

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  9. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  10. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  11. 2016Colorful Image Colorizationcited by 1,113
  12. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
27 more
  1. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  2. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  3. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  4. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  5. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 560
  6. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  7. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  8. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  9. 2019On Mutual Information Maximization for Representation Learningcited by 315
  10. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  11. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  12. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  13. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  14. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  15. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  16. 2017Representation Learning by Learning to Countcited by 120
  17. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  18. 2017Weakly Supervised Action Localization by Sparse Temporal Pooling Networkcited by 100
  19. 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
  20. 2018ClusterGAN : Latent Space Clustering in Generative Adversarial Networkscited by 75
  21. 2020Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Imagescited by 52
  22. 2020Iterative energy-based projection on a normal data manifold for anomaly localizationcited by 47
  23. 2018AVID: Adversarial Visual Irregularity Detectioncited by 19
  24. 2019Unsupervised Learning of Anomaly Detection from Contaminated Image Data using Simultaneous Encoder Trainingcited by 9
  25. 2019Attention Guided Anomaly Localization in Imagescited by 9
  26. 2019Exploring Deep Anomaly Detection Methods Based on Capsule Netcited by 7
  27. 2018Pathological Evidence Exploration in Deep Retinal Image Diagnosiscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 1; 2024: 3; 2025: 2; 2026: 1.

12 papers.

  1. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  2. 2022Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Surveycited by 67
  3. 2022A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Imagescited by 21
  4. 2022Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimationcited by 20
  5. 2026Failure Identification in Imitation Learning Via Statistical and Semantic Filteringcited by 6
  6. 2025A Survey on Foundation-Model-Based Industrial Defect Detectioncited by 5
  7. 2024IPAD: Industrial Process Anomaly Detection Datasetcited by 3
  8. 2022Unsupervised Industrial Anomaly Detection via Pattern Generative and Contrastive Networkscited by 2
  9. 2024Label-free Anomaly Detection in Aerial Agricultural Images with Masked Image Modelingcited by 2
  10. 2024Critical Review for One-class Classification: recent advances and the reality behind themcited by 2
  11. 2022Supervised Anomaly Detection Method Combining Generative Adversarial Networks and Three-Dimensional Data in Vehicle Inspectionscited by 0
  12. 2025Defect-aware Hybrid Prompt Optimization via Progressive Tuning for Zero-Shot Multi-type Anomaly Detection and Segmentationcited by 0