mlsanityData to 14 Oct 2026

A Survey on Foundation-Model-Based Industrial Defect Detection

arXiv 2502.19106 ↗First posted 26 Feb 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

As industrial products become abundant and sophisticated, visual industrial defect detection receives much attention, including two-dimensional and three-dimensional visual feature modeling. Traditional methods use statistical analysis, abnormal data synthesis modeling, and generation-based models to separate product defect features and complete defect detection. Recently, the emergence of foundation models has brought visual and textual semantic prior knowledge. Many methods are based on foundation models (FM) to improve the accuracy of detection, but at the same time, increase model complexity and slow down inference speed. Some FM-based methods have begun to explore lightweight modeling ways, which have gradually attracted attention and deserve to be systematically analyzed. In this paper, we conduct a systematic survey with comparisons and discussions of foundation model methods from different aspects and briefly review non-foundation model (NFM) methods recently published. Furthermore, we discuss the differences between FM and NFM methods from training objectives, model structure and scale, model performance, and potential directions for future exploration. Through comparison, we find FM methods are more suitable for few-shot and zero-shot learning, which are more in line with actual industrial application scenarios and worthy of in-depth research.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 104 of its 124 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

104 of 124 references.

References · 104

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2022Training language models to follow instructions with human feedbackcited by 15,971
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2023Segment Anythingcited by 8,234
  6. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  8. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  9. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  10. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  11. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 681
  12. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 564
38 more
  1. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 514
  2. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  3. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  4. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  5. 2021CRIS: CLIP-Driven Referring Image Segmentationcited by 353
  6. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  7. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  8. 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
  9. 2023SimpleNet: A Simple Network for Image Anomaly Detection and Localizationcited by 256
  10. 2021FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flowscited by 227
  11. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  12. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  13. 2023Multimodal Industrial Anomaly Detection via Hybrid Fusioncited by 139
  14. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  15. 2023APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADcited by 130
  16. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  17. 2022Asymmetric Student-Teacher Networks for Industrial Anomaly Detectioncited by 117
  18. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  19. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 116
  20. 2023SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understandingcited by 111
  21. 2023AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Modelcited by 111
  22. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  23. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  24. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 93
  25. 2023Real3D-AD: A Dataset of Point Cloud Anomaly Detectioncited by 87
  26. 2023Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detectioncited by 75
  27. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  28. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  29. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  30. 2023Few-Shot Defect Image Generation via Defect-Aware Feature Manipulationcited by 67
  31. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  32. 2023CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detectioncited by 58
  33. 2023Collaborative Discrepancy Optimization for Reliable Image Anomaly Localizationcited by 57
  34. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  35. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  36. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationcited by 50
  37. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  38. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45

50 most cited of 104 All 104 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 5.

5 papers.

  1. 2025AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detectioncited by 28
  2. 2025LR-IAD:Mask-Free Industrial Anomaly Detection with Logical Reasoningcited by 9
  3. 2025AgentIAD: Agentic Industrial Anomaly Detection via Adaptive Memory Augmentationcited by 4
  4. 2025Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Thingscited by 1
  5. 2025NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learningcited by 0