mlsanityData to 14 Oct 2026

Test Time Training for Industrial Anomaly Segmentation

arXiv 2404.03743 ↗First posted 4 Apr 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical applications require producing a binary segmentation to identify anomalies. Due to the absence of labeled anomalies in many real scenarios, standard practices binarize these maps based on some statistics derived from a validation set containing only nominal samples, resulting in poor segmentation performance. This paper addresses this problem by proposing a test time training strategy to improve the segmentation performance. Indeed, at test time, we can extract rich features directly from anomalous samples to train a classifier that can discriminate defects effectively. Our general approach can work downstream to any AD&S method that provides an anomaly score map as output, even in multimodal settings. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

43 of 56 references.

References · 43

  1. 2023Segment Anythingcited by 8,234
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 2016Wide Residual Networkscited by 3,070
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2020Point Transformercited by 1,470
  7. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 848
  8. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  9. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  10. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  11. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  12. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
31 more
  1. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
  2. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  3. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  4. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  5. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
  6. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  7. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  8. 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
  9. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  10. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  11. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  12. 2021The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localizationcited by 178
  13. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  14. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  15. 2021Student-Teacher Feature Pyramid Matching for Anomaly Detectioncited by 146
  16. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  17. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  18. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  19. 2020Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detectioncited by 115
  20. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  21. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  22. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  23. 2021Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detectioncited by 83
  24. 2022MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiescited by 68
  25. 2021SITA: Single Image Test-time Adaptationcited by 59
  26. 2020DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentationcited by 54
  27. 2023Multimodal Industrial Anomaly Detection by Crossmodal Feature Mappingcited by 42
  28. 2020MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detectioncited by 31
  29. 2022Ev-TTA: Test-Time Adaptation for Event-Based Object Recognitioncited by 26
  30. 2023To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentationcited by 14
  31. 2023Single Image Test-Time Adaptation for Segmentationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025SiM3D: Single-instance Multiview Multimodal and Multisetup 3D Anomaly Detection Benchmarkcited by 5
  2. 2025Test Time Training for 4D Medical Image Interpolationcited by 0
  3. 2026Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chainingcited by 0
  4. 2026Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentationcited by 0