mlsanityData to 14 Oct 2026

MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection

arXiv 2504.12970 ↗First posted 17 Apr 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Currently, industrial anomaly detection suffers from two bottlenecks: (i) the rarity of real-world defect images and (ii) the opacity of sample quality when synthetic data are used. Existing synthetic strategies (e.g., cut-and-paste) overlook the underlying physical causes of defects, leading to inconsistent, low-fidelity anomalies that hamper model generalization to real-world complexities. In this paper, we introduce a novel and lightweight pipeline that generates synthetic anomalies through Math-Phys model guidance, refines them via a Coarse-to-Fine approach and employs a bi-level optimization strategy with a Synthesis Quality Estimator (SQE). By combining physical modeling of the three most typical physics-driven defect mechanisms: Fracture Line (FL), Pitting Loss (PL), and Plastic Warpage (PW), our method produces realistic defect masks, which are subsequently enhanced in two phases. The first stage (npcF) enforces a PDE-based consistency to achieve a globally coherent anomaly structure, while the second stage (npcF++) further improves local fidelity. Additionally, we leverage SQE-driven weighting, ensuring that high-quality synthetic samples receive greater emphasis during training. To validate our method, we conduct experiments on three anomaly detection benchmarks: MVTec AD, VisA, and BTAD. Across these datasets, our method achieves state-of-the-art results in both image- and pixel-AUROC, confirming the effectiveness of our MaPhC2F dataset and BiSQAD method. All code will be released.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 17 Apr 2025.

Builds on

29 of 44 references.

References · 29

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  4. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  5. 2019Meta-Learning with Implicit Gradientscited by 525
  6. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  7. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  8. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  9. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  10. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  11. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  12. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
17 more
  1. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  2. 2022Diffusion Models for Medical Anomaly Detectioncited by 232
  3. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  4. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  5. 2021Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localizationcited by 116
  6. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  7. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  8. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 90
  9. 2023On Diffusion Modeling for Anomaly Detectioncited by 72
  10. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  11. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  12. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  13. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  14. 2024Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentationcited by 11
  15. 2023A Comprehensive Augmentation Framework for Anomaly Detectioncited by 8
  16. 2024Enhancing Anomaly Detection via Generating Diversified and Hard-to-distinguish Synthetic Anomaliescited by 3
  17. 2024Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detectioncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detectioncited by 2