mlsanityData to 14 Oct 2026

SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation

arXiv 2207.14315 ↗First posted 28 Jul 2022cs.CVcited by 400

Not on the map. Why?

Cited by 45 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class and 2-class 5/10/high-shot training setups. We release the Visual Anomaly (VisA) Dataset consisting of 10,821 high-resolution color images (9,621 normal and 1,200 anomalous samples) covering 12 objects in 3 domains, making it the largest industrial anomaly detection dataset to date. Both image and pixel-level labels are provided. We also propose a new self-supervised framework - SPot-the-difference (SPD) - which can regularize contrastive self-supervised pre-training, such as SimSiam, MoCo and SimCLR, to be more suitable for anomaly detection tasks. Our experiments on VisA and MVTec-AD dataset show that SPD consistently improves these contrastive pre-training baselines and even the supervised pre-training. For example, SPD improves Area Under the Precision-Recall curve (AU-PR) for anomaly segmentation by 5.9% and 6.8% over SimSiam and supervised pre-training respectively in the 2-class high-shot regime. We open-source the project at http://github.com/amazon-research/spot-diff .

Key facts. Cited by 400 papers in the map (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 28 Jul 2022.

Builds on

35 of 47 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2016Wide Residual Networkscited by 3,070
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  10. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  12. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
23 more
  1. 2016Colorful Image Colorizationcited by 1,114
  2. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  3. 2020PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localizationcited by 594
  4. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  5. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  6. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  7. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  8. 2022Anomaly Detection via Reverse Distillation from One-Class Embeddingcited by 421
  9. 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
  10. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 300
  11. 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
  12. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  13. 2021Self-Supervised Representation Learning: Introduction, Advances and Challengescited by 148
  14. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  15. 2021Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detectioncited by 119
  16. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  17. 2018Learning to Describe Differences Between Pairs of Similar Imagescited by 114
  18. 2021Instance Localization for Self-supervised Detection Pretrainingcited by 99
  19. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 88
  20. 2014Toward Supervised Anomaly Detectioncited by 73
  21. 2020Self-EMD: Self-Supervised Object Detection without ImageNetcited by 70
  22. 2021MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Drivingcited by 41
  23. 2020On the surprising similarities between supervised and self-supervised modelscited by 29

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 45; 2024: 102; 2025: 121; 2026: 127.

400 papers.

Sort:

By area:

  1. 2023WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentationcited by 315
  2. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  3. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
  4. 2023EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latenciescited by 160
  5. 2023Deep Industrial Image Anomaly Detection: A Surveycited by 148
  6. 2024Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detectioncited by 139
  7. 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
  8. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  9. 2024RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detectioncited by 116
  10. 2024MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detectioncited by 113
  11. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  12. 2024Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detectioncited by 93
38 more
  1. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  2. 2024A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localizationcited by 74
  3. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  4. 2022PNI : Industrial Anomaly Detection using Position and Neighborhood Informationcited by 69
  5. 2024A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospectcited by 69
  6. 2023Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Networkcited by 67
  7. 2023IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturingcited by 64
  8. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  9. 2023ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstructioncited by 63
  10. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  11. 2024A Closer Look at AUROC and AUPRC under Class Imbalancecited by 57
  12. 2023Anomaly Detection with Conditioned Denoising Diffusion Modelscited by 56
  13. 2025Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Modelscited by 54
  14. 2024AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2cited by 53
  15. 2024MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Imagescited by 52
  16. 2024FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localizationcited by 51
  17. 2024VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationcited by 50
  18. 2024ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentationcited by 49
  19. 2025Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detectioncited by 48
  20. 2023Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detectioncited by 47
  21. 2024MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detectioncited by 47
  22. 2023DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detectioncited by 46
  23. 2023PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detectioncited by 46
  24. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  25. 2023TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detectioncited by 43
  26. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detectioncited by 42
  27. 2023Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detectioncited by 39
  28. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  29. 2024MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detectioncited by 35
  30. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  31. 2025Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detectioncited by 31
  32. 2022MAEDAY: MAE for few and zero shot AnomalY-Detectioncited by 30
  33. 2025The MVTec AD 2 Dataset: Advanced Scenarios for Unsupervised Anomaly Detectioncited by 30
  34. 2024Effectiveness Assessment of Recent Large Vision-Language Modelscited by 29
  35. 2024GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Featurescited by 29
  36. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  37. 2025InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialoguecited by 29
  38. 2024Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detectioncited by 28

50 most cited of 400 All 400 (JSON)