mlsanityData to 7 Oct 2026

HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization

arXiv 2208.03486 ↗First posted 6 Aug 2022cs.CV cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Unsupervised anomaly detection and localization is a crucial task as it is impossible to collect and label all possible anomalies. Many studies have emphasized the importance of integrating local and global information to achieve accurate segmentation of anomalies. To this end, there has been a growing interest in Transformer, which allows modeling long-range content interactions. However, global interactions through self attention are generally too expensive for most image scales. In this study, we introduce HaloAE, the first auto-encoder based on a local 2D version of Transformer with HaloNet. With HaloAE, we have created a hybrid model that combines convolution and local 2D block-wise self-attention layers and jointly performs anomaly detection and segmentation through a single model. We achieved competitive results on the MVTec dataset, suggesting that vision models incorporating Transformer could benefit from a local computation of the self-attention operation, and pave the way for other applications.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 6 Aug 2022.

Builds on

43 of 56 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  9. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  12. 2021Transformers in Vision: A Surveycited by 1,009
31 more
  1. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  2. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  3. 2018Image Transformercited by 770
  4. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  5. 2021Transformer in Transformercited by 632
  6. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  7. 2018Real-world Anomaly Detection in Surveillance Videoscited by 570
  8. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  9. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  10. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  11. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  12. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  13. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  14. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  15. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  16. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  17. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  18. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  19. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 222
  20. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  21. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  22. 2020Classification-Based Anomaly Detection for General Datacited by 210
  23. 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
  24. 2020Explainable Deep One-Class Classificationcited by 126
  25. 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
  26. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  27. 2020Multi-Loss Weighting with Coefficient of Variationscited by 36
  28. 2018q-Space Novelty Detection with Variational Autoencoderscited by 22
  29. 2016Identifying and Categorizing Anomalies in Retinal Imaging Datacited by 18
  30. 2016Self-Paced Multi-Task Learningcited by 13
  31. 2022Aggregating Global Features into Local Vision Transformercited by 10

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2.

5 papers.

  1. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 147
  2. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  3. 2023A survey of the Vision Transformers and their CNN-Transformer based Variantscited by 33
  4. 2024Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detectioncited by 0
  5. 2024Evaluating Vision Transformer Models for Visual Quality Control in Industrial Manufacturingcited by 0