mlsanityData to 7 Oct 2026

Noise & pattern: identity-anchored Tikhonov regularization for robust structural anomaly detection

arXiv 2511.07233 ↗First posted 10 Nov 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Anomaly detection plays a pivotal role in automated industrial inspection, aiming to identify subtle or rare defects in otherwise uniform visual patterns. As collecting representative examples of all possible anomalies is infeasible, we tackle structural anomaly detection using a self-supervised autoencoder that learns to repair corrupted inputs. To this end, we introduce a corruption model that injects artificial disruptions into training images to mimic structural defects. While reminiscent of denoising autoencoders, our approach differs in two key aspects. First, instead of unstructured i.i.d. noise, we apply structured, spatially coherent perturbations that make the task a hybrid of segmentation and inpainting. Second, and counterintuitively, we add and preserve Gaussian noise on top of the occlusions, which acts as a Tikhonov regularizer anchoring the Jacobian of the reconstruction function toward identity. This identity-anchored regularization stabilizes reconstruction and further improves both detection and segmentation accuracy. On the MVTec AD benchmark, our method achieves state-of-the-art results (I/P-AUROC: 99.9/99.4), supporting our theoretical framework and demonstrating its practical relevance for automatic inspection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 76 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

35 of 76 references.

References · 35

  1. 2013Describing Textures in the Wildcited by 2,110
  2. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
  4. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  5. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 591
  6. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  7. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  8. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  9. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  10. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  11. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  12. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
23 more
  1. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  2. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  3. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 263
  4. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  5. 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 193
  6. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  7. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  8. 2019Towards Visually Explaining Variational Autoencoderscited by 113
  9. 2021Inpainting Transformer for Anomaly Detectioncited by 91
  10. 2018Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoderscited by 83
  11. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  12. 2019Unsupervised Anomaly Localization using Variational Auto-Encoderscited by 73
  13. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  14. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  15. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  16. 2021Detecting Outliers with Poisson Image Interpolationcited by 44
  17. 2020Improved anomaly detection by training an autoencoder with skip connections on images corrupted with Stain-shaped noisecited by 39
  18. 2024Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detectioncited by 35
  19. 2018Anomaly Detection using Deep Learning based Image Completioncited by 27
  20. 2017Robust, Deep and Inductive Anomaly Detectioncited by 24
  21. 2018Detecting Anomalous Faces with 'No Peeking' Autoencoderscited by 5
  22. 2017Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFscited by 4
  23. 2023Active anomaly detection based on deep one-class classificationcited by 3

Built on by

Not cited yet.