Awesome

Awesome Industrial Anomaly Detection

We discuss public datasets and related studies in detail. Welcome to read our paper and make comments.

Deep Industrial Image Anomaly Detection: A Survey (Machine Intelligence Research)

IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing [TCYB 2024][code][中文]

We will keep focusing on this field and updating relevant information.

Keywords: anomaly detection, anomaly segmentation, industrial image, defect detection

[Main Page] [Survey] [Benchmark] [Result]

🔥🔥🔥 Contributions to our repository are welcome. Feel free to categorize the papers.

🔥🔥🔥 Which MLLM performs best in industrial anomaly detection? Please refer to our recent research, which evaluates state-of-the-art models, including GPT-4o, Gemini-1.5, LLaVA-Next, and InternVL.

[2024.10.16] We are proud to announce the launch of MMAD, the first-ever comprehensive benchmark for Multimodal Large Language Models in Industrial Anomaly Detection! 🌟 [Paper] [Code] [Data]

Table of Contents

• Awesome Industrial Anomaly Detection
  • Table of Contents
• SOTA methods with code
• Recommended Benchmarks
• Recent research
  • NeurIPS 2024
  • ECCV 2024
  • ACM MM 2024
  • ICASSP 2024
  • CVPR 2024
  • ICLR 2024
  • AAAI 2024
  • WACV 2024
  • NeurIPS 2023
  • LLM related
  • SAM segment anything
  • Others
  • Medical (related)
• Paper Tree (Classification of representative methods)
• Timeline
• Paper list for industrial image anomaly detection
• Related Survey, Benchmark, and Framework
• 2 Unsupervised AD
  • 2.1 Feature-Embedding-based Methods
    • 2.1.1 Teacher-Student
    • 2.1.2 One-Class Classification (OCC)
    • 2.1.3 Distribution-Map
    • 2.1.4 Memory Bank
    • 2.1.5 Vison Language AD
  • 2.2 Reconstruction-Based Methods
    • 2.2.1 Autoencoder (AE)
    • 2.2.2 Generative Adversarial Networks (GANs)
    • 2.2.3 Transformer
    • 2.2.4 Diffusion Model
    • 2.2.5 Others
  • 2.3 Supervised AD
    • More Normal samples With (Less Abnormal Samples or Weak Labels)
    • More Abnormal Samples
• 3 Other Research Direction
  • 3.1 Zero/Few-Shot AD
    • Zero-Shot AD
    • Few-Shot AD
  • 3.2 Noisy AD
  • 3.3 Anomaly Synthetic
  • 3.4 RGBD AD
  • 3.5 3D AD
  • 3.6 Continual AD
  • 3.7 Uniform/Multi-Class AD
  • 3.8 Logical AD
  • Other settings
    • TTT binary segmentation
    • MoE with TTA
    • Adversary Attack
    • Defect Classification
• 4 Dataset
  • BibTex Citation
  • Star History

SOTA methods with code

Title	Venue	Date	Code	topic
<br> Anomaly Detection via Reverse Distillation from One-Class Embedding <br>	CVPR	2022	Github	Teacher-Student
<br> Revisiting Reverse Distillation for Anomaly Detection <br>	CVPR	2023	Github	Teacher-Student
<br> SimpleNet: A Simple Network for Image Anomaly Detection and Localization <br>	CVPR	2023	Github	One-Class-Classification
<br> Real-time unsupervised anomaly detection with localization via conditional normalizing flows <br>	WACV	2022	Github	Distribution Map
<br> PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow <br>	CVPR	2023	Github	Distribution Map
<br> Towards total recall in industrial anomaly detection <br>	CVPR	2022	Github	Memory-bank
<br> PNI: Industrial Anomaly Detection using Position and Neighborhood Information <br>	ICCV	2023	Github	Memory-bank
<br> Draem-a discriminatively trained reconstruction embedding for surface anomaly detection <br>	ICCV	2021	Github	Reconstruction-based
<br> DSR: A dual subspace re-projection network for surface anomaly detection <br>	ECCV	2022	Github	Reconstruction-based
<br> Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection <br>	TIP	2023	Github	Reconstruction-based
<br> RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection <br>	CVPR	2024	Github	Reconstruction-based
<br> Registration based few-shot anomaly detection <br>	ECCV	2022	Github	Few Shot
<br> AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models <br>	AAAI	2024	Github	Few Shot
<br> Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection <br>	CVPR	2022	Github	Few abnormal samples
<br> Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection <br>	CVPR	2023	Github	Few abnormal samples
<br> Deep one-class classification via interpolated gaussian descriptor <br>	AAAI	2022	Github	Noisy AD
<br> SoftPatch: Unsupervised Anomaly Detection with Noisy Data <br>	NeurIPS	2022	Github	Noisy AD
<br> Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification <br>	ICCV	2023	Github	Noisy AD
<br> Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt <br>	AAAI	2024	Github	Continual AD
<br> A Unified Model for Multi-class Anomaly Detection <br>	NeurIPS	2022	Github	Multi-class unified
<br> Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection <br>	NeurIPS	2023	Github	Multi-class unified
<br> Multimodal Industrial Anomaly Detection via Hybrid Fusion <br>	CVPR	2023	Github	RGBD
<br> Real3D-AD: A Dataset of Point Cloud Anomaly Detection <br>	NeurIPS	2023	Github	Point Cloud
<br> AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization <br>	arxiv	2023	Github	Zero Shot
<br> Segment Any Anomaly without Training via Hybrid Prompt Regularization <br>	arxiv	2023	Github	Zero Shot
<br> PSAD: Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection <br>	AAAI	2024	Github	Logical/Few Shot
<br> UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection <br>	arxiv	2023	Github	Multi-class unified

Recommended Benchmarks

Title	Venue	Date	Code	topic
<br> Anomalib: A Deep Learning Library for Anomaly Detection <br>	ICIP	2022	Github	Benchmark
<br> IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing <br>	TCYB	2024	Github	Benchmark
<br> ADer: A Comprehensive Benchmark for Multi-class Visual Anomaly Detection <br>	arxiv	2024	Github	Benchmark
<br> MMAD: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection <br>	arxiv	2024	Github	Benchmark

• Anomaly Detection on MVTec AD [paper with code]
• Anomaly Detection on VisA [paper with code]
• Anomaly Detection on MVTec LOCO AD [paper with code]
• Anomaly Detection on MVTec 3D-AD [paper with code]
• Anomaly Detection Datasets and Benchmarks [paper with code]

Recent research

NeurIPS 2024

• MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection [NeurIPS 2024][code]
• PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection [NeurIPS 2024][code]
• CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset [NeurIPS 2024][data]
• ResAD: A Simple Framework for Class Generalizable Anomaly Detection [NeurIPS 2024][code]

ECCV 2024

• R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [ECCV 2024][homepage]
• An Incremental Unified Framework for Small Defect Inspection [ECCV2024][code]
• Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection [ECCV 2024][code]
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [ECCV 2024]
• Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt [ECCV 2024][code]
• Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation [ECCV 2024][code]
• AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection [ECCV 2024][code]
• GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [ECCV 2024][code]
• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [ECCV 2024][code]
• VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation [ECCV 2024][code]
• A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization [ECCV 2024][code]
• Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection [ECCV 2024][code]
• TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection [ECCV 2024][code]
• Continuous Memory Representation for Anomaly Detection [ECCV 2024][homepage][code]
• Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics [ECCV 2024][data]
• AD3: Introducing a score for Anomaly Detection Dataset Difficulty assessment using VIADUCT dataset [ECCV 2024]
• Learning Diffusion Models for Multi-View Anomaly Detection [ECCV 2024]
• MoEAD: A Parameter-efficient Model for Multi-class Anomaly Detection [ECCV 2024][code]
• Unsupervised, Online and On-The-Fly Anomaly Detection For Non-Stationary Image Distributions [ECCV 2024][code]
• Tackling Structural Hallucination in Image Translation with Local Diffusion [ECCV 2024 oral][code]

ACM MM 2024

• FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization [ACM MM 2024][code]
• Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection [ACM MM 2024]
• FOCT: Few-shot Industrial Anomaly Detection with Foreground-aware Online Conditional Transport [ACM MM 2024]
• Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning [ACM MM 2024][code]

ICASSP 2024

• Implicit Foreground-Guided Network for Anomaly Detection and Localization [ICASSP 2024]
• Neural Network Training Strategy To Enhance Anomaly Detection Performance: A Perspective On Reconstruction Loss Amplification [ICASSP 2024]
• Patch-Wise Augmentation for Anomaly Detection and Localization [ICASSP 2024]
• A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation [ICASSP 2024]
• Feature-Constrained and Attention-Conditioned Distillation Learning for Visual Anomaly Detection [ICASSP 2024]
• CAGEN: Controllable Anomaly Generator using Diffusion Model [ICASSP 2024]
• Mixed-Attention Auto Encoder for Multi-Class Industrial Anomaly Detection [ICASSP 2024]

CVPR 2024

• Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation [CVPR 2024][code]
• RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection [CVPR 2024][code]
• Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts [CVPR 2024][code]
• Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping [CVPR 2024]
• Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network [CVPR 2024][code]
• Real-IAD: A Real-World Multi-view Dataset for Benchmarking Versatile Industrial Anomaly Detection [CVPR 2024][code][data]
• Long-Tailed Anomaly Detection with Learnable Class Names [CVPR 2024][data split]
• PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection [CVPR 2024][code]
• Supervised Anomaly Detection for Complex Industrial Images [CVPR 2024][code]
• Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection [CVPR 2024][code]
• Prompt-enhanced Multiple Instance Learning for Weakly Supervised Anomaly Detection [CVPR 2024][code]
• Looking 3D: Anomaly Detection with 2D-3D Alignment [CVPR 2024][homepage][code]
• CVPRW: VAND 2.0: Visual Anomaly and Novelty Detection - 2nd Edition [Challenge and Call for Papers]
• Divide and Conquer: High-Resolution Industrial Anomaly Detection via Memory Efficient Tiled Ensemble [CVPR 24 Visual Anomaly Detection Workshop][homepage]

ICLR 2024

• AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection [ICLR 2024][code]
• MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images[ICLR 2024][code]

AAAI 2024

• Rethinking Reverse Distillation for Multi-Modal Anomaly Detection [AAAI 2024]
• Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [AAAI 2024][code]
• Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection [AAAI 2024][code]
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [AAAI 2024][code]
• Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection [AAAI 2024]
• AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [AAAI 2024][code]
• AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [AAAI 2024][code][project page]
• A Comprehensive Augmentation Framework for Anomaly Detection [AAAI 2024]

WACV 2024

• ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection [WACV 2024]
• Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining [WACV 2024][code]
• EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies [WACV 2024]
• Contextual Affinity Distillation for Image Anomaly Detection [WACV 2024]
• Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study [WACV 2024]
• PromptAD: Zero-shot Anomaly Detection using Text Prompts [WACV 2024]
• High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis [WACV 2024]
• Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation [WACV 2024][code]

NeurIPS 2023

• Real3D-AD: A Dataset of Point Cloud Anomaly Detection [NeurIPS 2023][code][中文]
• PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection [NeurIPS 2023][code]
• Zero-Shot Anomaly Detection via Batch Normalization [NeurIPS 2023][code]
• SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection and Localization [NeurIPS 2023]
• Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach [NeurIPS 2023]
• Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection [NeurIPS 2023][code]
• ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction [NeurIPS 2023][code]

LLM related

• Myriad: Large Multimodal Model by Applying Vision Experts for Industrial Anomaly Detection [2023][code]
• AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [AAAI 2024][code][project page]
• The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) [2023 Section 9.2]
• Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead [2023][code]
• Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection [2023][code]
• Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning [2024]
• Do LLMs Understand Visual Anomalies? Uncovering LLM Capabilities in Zero-shot Anomaly Detection [2024]
• LogiCode: an LLM-Driven Framework for Logical Anomaly Detection [2024]
• FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queries [ICCAD 2024]
• VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection [2024]

SAM segment anything

• Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications [2023 SAM tech report]
• SAM Struggles in Concealed Scenes -- Empirical Study on "Segment Anything" [2023 SAM tech report]
• Segment Any Anomaly without Training via Hybrid Prompt Regularization [2023] [code]
• Application of Segment Anything Model for Civil Infrastructure Defect Assessment [2023 SAM tech report]
• Segment Anything in Defect Detection [2023]
• Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [AAAI 2024][code]
• ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [2023]
• A SAM-guided Two-stream Lightweight Model for Anomaly Detection [2024][code]
• Inspiring the Next Generation of Segment Anything Models: Comprehensively Evaluate SAM and SAM 2 with Diverse Prompts Towards Context-Dependent Concepts under Different Scenes [2024][code]

Others

• Self-supervised Context Learning for Visual Inspection of Industrial Defects [2023][code]
• CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection [2023]
• Self-Tuning Self-Supervised Anomaly Detection [2023]
• Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data [2023]
• A Discrepancy Aware Framework for Robust Anomaly Detection [2023][code]
• The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) [2023 Section 9.2]
• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [2023]
• Decision Fusion Network with Perception Fine-tuning for Defect Classification [2023]
• FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection [2023][code]
• AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization [2023][code]
• End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection [2023]
• CVPR 1st workshop on Vision-based InduStrial InspectiON [CVPR 2023 Workshop] [data link]
• Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection [2023]
• How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection [Dataset Distillation][2023]
• Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection [2023]
• AUPIMO: Redefining Visual Anomaly Detection Benchmarks with High Speed and Low Tolerance [2024]
• Model Selection of Zero-shot Anomaly Detectors in the Absence of Labeled Validation Data [2024]
• PUAD: Frustratingly Simple Method for Robust Anomaly Detection [2024]
• COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection [TIP2024]
• PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Features [2024]
• Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection [2024]
• RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection [CASE 2024][github page]
• Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework [2024][code]

Medical (related)

• Towards Universal Unsupervised Anomaly Detection in Medical Imaging [2024]
• MAEDiff: Masked Autoencoder-enhanced Diffusion Models for Unsupervised Anomaly Detection in Brain Images [2024]
• BMAD: Benchmarks for Medical Anomaly Detection [2023]
• Unsupervised Pathology Detection: A Deep Dive Into the State of the Art [2023]
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [CVPR 2024]
• Multi-Image Visual Question Answering for Unsupervised Anomaly Detection [2024]

Paper Tree (Classification of representative methods)

Timeline

Paper list for industrial image anomaly detection

Related Survey, Benchmark, and Framework

• A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure [2015]
• Visual-based defect detection and classification approaches for industrial applications: a survey [2020]
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges [TMLR 2022]
• Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey [TIM 2022]
• A Survey on Unsupervised Industrial Anomaly Detection Algorithms [2022]
• A Survey of Methods for Automated Quality Control Based on Images [IJCV 2023][github page]
• Benchmarking Unsupervised Anomaly Detection and Localization [2022]
• IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing [TCYB 2024][code][中文]
• A Deep Learning-based Software for Manufacturing Defect Inspection [TII 2017][code]
• Anomalib: A Deep Learning Library for Anomaly Detection [ICIP 2022][code]
• Ph.D. thesis of Paul Bergmann(The first author of MVTec AD series) [2022]
• CVPR 2023 Tutorial on "Recent Advances in Anomaly Detection" [CVPR Workshop 2023][video]
• Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection [2023][code]
• A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect [2024]
• AUPIMO: Redefining Visual Anomaly Detection Benchmarks with High Speed and Low Tolerance [2024]
• Explainable Anomaly Detection in Images and Videos: A Survey [2024][repo]
• RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection [CASE 2024][github page]
• Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey [2024][github page]
• Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey [2024][github page]
• A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly Detection [2024][github page]
• OpenOOD: Benchmarking Generalized Out-of-Distribution Detection [NeurIPS2022v1][2024v1.5][github page]

2 Unsupervised AD

2.1 Feature-Embedding-based Methods

2.1.1 Teacher-Student

• Contextual Affinity Distillation for Image Anomaly Detection [WACV 2024]
• Revisiting Reverse Distillation for Anomaly Detection [CVPR 2023] [code]
• Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings [CVPR 2020]
• Multiresolution knowledge distillation for anomaly detection [CVPR 2021]
• Glancing at the Patch: Anomaly Localization With Global and Local Feature Comparison [CVPR 2021]
• Reconstruction Student with Attention for Student-Teacher Pyramid Matching [2021]
• Student-Teacher Feature Pyramid Matching for Anomaly Detection [2021][code]
• PFM and PEFM for Image Anomaly Detection and Segmentation [CASE 2022] [TII 2022][code]
• Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection [2022]
• Anomaly Detection via Reverse Distillation from One-Class Embedding [CVPR 2022][code]
• Asymmetric Student-Teacher Networks for Industrial Anomaly Detection [WACV 2022][code]
• Informative knowledge distillation for image anomaly segmentation [2022][code]
• Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection [ICCV 2023]
• A Discrepancy Aware Framework for Robust Anomaly Detection [2023][code]
• Enhanced multi-scale features mutual mapping fusion based on reverse knowledge distillation for industrial anomaly detection and localization [TBD 2024]
• AEKD: Unsupervised auto-encoder knowledge distillation for industrial anomaly detection [JMS 2024]
• Masked feature regeneration based asymmetric student–teacher network for anomaly detection [Multimedia Tools and Applications 2024]
• Feature-Constrained and Attention-Conditioned Distillation Learning for Visual Anomaly Detection [ICASSP 2024]
• MiniMaxAD: A Lightweight Autoencoder for Feature-Rich Anomaly Detection [2024]

2.1.2 One-Class Classification (OCC)

• Patch svdd: Patch-level svdd for anomaly detection and segmentation [ACCV 2020]
• Anomaly detection using improved deep SVDD model with data structure preservation [2021]
• A Semantic-Enhanced Method Based On Deep SVDD for Pixel-Wise Anomaly Detection [2021]
• MOCCA: Multilayer One-Class Classification for Anomaly Detection [2021]
• Defect Detection of Metal Nuts Applying Convolutional Neural Networks [2021]
• Panda: Adapting pretrained features for anomaly detection and segmentation [2021]
• Mean-shifted contrastive loss for anomaly detection [2021]
• Learning and Evaluating Representations for Deep One-Class Classification [2020]
• Self-supervised learning for anomaly detection with dynamic local augmentation [2021]
• Contrastive Predictive Coding for Anomaly Detection [2021]
• Cutpaste: Self-supervised learning for anomaly detection and localization [ICCV 2021][unofficial code]
• Consistent estimation of the max-flow problem: Towards unsupervised image segmentation [2020]
• MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities [2022][unofficial code]
• SimpleNet: A Simple Network for Image Anomaly Detection and Localization [CVPR 2023][code]
• End-to-End Augmentation Hyperparameter Tuning for Self-Supervised Anomaly Detection [2023]
• Anomaly Detection under Distribution Shift [ICCV 2023][code]
• Learning Transferable Representations for Image Anomaly Localization Using Dense Pretraining [WACV 2024][code]
• GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features [ECCV 2024][code]
• A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization [ECCV 2024][code]
• Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection [ACM MM 2024]
• SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection [ICIP 2024][code]

2.1.3 Distribution-Map

• Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity [Sensors 2018]
• A Multi-Scale A Contrario method for Unsupervised Image Anomaly Detection [2021]
• Modeling the distribution of normal data in pre-trained deep features for anomaly detection [2021]
• Transfer Learning Gaussian Anomaly Detection by Fine-Tuning Representations [2021]
• PEDENet: Image anomaly localization via patch embedding and density estimation [2022]
• Unsupervised image anomaly detection and segmentation based on pre-trained feature mapping [2022]
• Position Encoding Enhanced Feature Mapping for Image Anomaly Detection [2022][code]
• Focus your distribution: Coarse-to-fine non-contrastive learning for anomaly detection and localization [ICME 2022]
• Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework [2021][code]
• Fastflow: Unsupervised anomaly detection and localization via 2d normalizing flows [2021][unofficial code]
• Same same but differnet: Semi-supervised defect detection with normalizing flows [WACV 2021][code]
• Fully convolutional cross-scale-flows for image-based defect detection [WACV 2022][code]
• Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows [WACV 2022][code]
• CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks [2022]
• AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection [2022]
• Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization [TII 2023][code]
• PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow [CVPR 2023][code]
• Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study [WACV 2024]
• Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning [ICML 2023]
• FRAnomaly: flow-based rapid anomaly detection from images [Applied Intelligence 2024]
• Image alignment-based patch distribution framework for anomaly detection [ICCVDM 2024]
• MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection [2024][code]

2.1.4 Memory Bank

• ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection [WACV 2024]
• Sub-image anomaly detection with deep pyramid correspondences [2020]
• Semi-orthogonal embedding for efficient unsupervised anomaly segmentation [2021]
• Anomaly Detection Via Self-Organizing Map [2021]
• PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization [ICPR 2021][unofficial code]
• Industrial Image Anomaly Localization Based on Gaussian Clustering of Pretrained Feature [2021]
• Towards total recall in industrial anomaly detection[CVPR 2022][code]
• CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization[2022][code]
• FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection[2022]
• N-pad: Neighboring Pixel-based Industrial Anomaly Detection [2022]
• Multi-scale patch-based representation learning for image anomaly detection and segmentation [2022]
• SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation [ECCV 2022]
• Diversity-Measurable Anomaly Detection [CVPR 2023]
• SelFormaly: Towards Task-Agnostic Unified Anomaly Detection[2023]
• REB: Reducing Biases in Representation for Industrial Anomaly Detection [2023][code]
• PNI : Industrial Anomaly Detection using Position and Neighborhood Information [ICCV 2023][code]
• Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification [ICCV 2023][code]
• Grid-Based Continuous Normal Representation for Anomaly Detection [2024][code]
• PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Features [2024]
• DMAD: Dual Memory Bank for Real-World Anomaly Detection [2024]
• A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation [ICASSP 2024]
• AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detection [ECCVW 2024]
• VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization [2024][code]
• FOCT: Few-shot Industrial Anomaly Detection with Foreground-aware Online Conditional Transport [ACM MM 2024]

2.1.5 Vison Language AD

• Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection [BMVC 2023]
• AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection [ICLR 2024][code]
• WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation [CVPR 2023]
• ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [2023]
• CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection [2023]
• AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization [2023][code]
• AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [AAAI 2024][code][project page]
• Anomaly Detection by Adapting a pre-trained Vision Language Model [2024]
• Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning [2024][code]
• PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection [CVPR 2024][code]
• Do LLMs Understand Visual Anomalies? Uncovering LLM Capabilities in Zero-shot Anomaly Detection [2024]
• FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization [2024]
• Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection [2024]
• AnoPLe: Few-Shot Anomaly Detection via Bi-directional Prompt Learning with Only Normal Samples [2024][code]
• GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection [2024]
• UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection [2024][code]

2.2 Reconstruction-Based Methods

2.2.1 Autoencoder (AE)

• Improving unsupervised defect segmentation by applying structural similarity to autoencoders [2018]
• Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model [Sensors 2018]
• An Unsupervised-Learning-Based Approach for Automated Defect Inspection on Textured Surfaces [TIM 2018]
• Unsupervised anomaly detection using style distillation [2020]
• Unsupervised two-stage anomaly detection [2021]
• Dfr: Deep feature reconstruction for unsupervised anomaly segmentation [Neurocomputing 2020]
• Unsupervised anomaly segmentation via multilevel image reconstruction and adaptive attention-level transition [2021]
• Encoding structure-texture relation with p-net for anomaly detection in retinal images [2020]
• Improved anomaly detection by training an autoencoder with skip connections on images corrupted with stain-shaped noise [2021]
• Unsupervised anomaly detection for surface defects with dual-siamese network [2022]
• Divide-and-assemble: Learning block-wise memory for unsupervised anomaly detection [ICCV 2021]
• Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection [2022][code]
• Spatial Contrastive Learning for Anomaly Detection and Localization [2022]
• Superpixel masking and inpainting for self-supervised anomaly detection [BMVC 2020]
• Iterative image inpainting with structural similarity mask for anomaly detection [2020]
• Self-Supervised Masking for Unsupervised Anomaly Detection and Localization [2022]
• Reconstruction by inpainting for visual anomaly detection [PR 2021]
• Draem-a discriminatively trained reconstruction embedding for surface anomaly detection [ICCV 2021][code]
• DSR: A dual subspace re-projection network for surface anomaly detection [ECCV 2022][code]
• Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization [ECCV 2022][code]
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [2022]
• Self-supervised predictive convolutional attentive block for anomaly detection [CVPR 2022 oral][code]
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [TPAMI 2022][code]
• Iterative energy-based projection on a normal data manifold for anomaly localization [2019]
• Towards visually explaining variational autoencoders [2020]
• Deep generative model using unregularized score for anomaly detection with heterogeneous complexity [2020]
• Anomaly localization by modeling perceptual features [2020]
• Image anomaly detection using normal data only by latent space resampling [2020]
• Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localization [2023]
• Patch-wise Auto-Encoder for Visual Anomaly Detection [2023]
• FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection [2023][code]
• Template-guided Hierarchical Feature Restoration for Anomaly Detection [ICCV 2023]
• FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction [ICCV 2023][code]
• Produce Once, Utilize Twice for Anomaly Detection [2023]
• RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection [CVPR 2024][code]
• Implicit Foreground-Guided Network for Anomaly Detection and Localization [ICASSP 2024]
• Neural Network Training Strategy To Enhance Anomaly Detection Performance: A Perspective On Reconstruction Loss Amplification [ICASSP 2024]
• Patch-Wise Augmentation for Anomaly Detection and Localization [ICASSP 2024]
• A Reconstruction-Based Feature Adaptation for Anomaly Detection with Self-Supervised Multi-Scale Aggregation [ICASSP 2024]
• Mixed-Attention Auto Encoder for Multi-Class Industrial Anomaly Detection [ICASSP 2024]
• Dual-Constraint Autoencoder and Adaptive Weighted Similarity Spatial Attention for Unsupervised Anomaly Detection [TII 2024]
• Multi-feature Reconstruction Network using Crossed-mask Restoration for Unsupervised Anomaly Detection [2024]
• R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [ECCV 2024][homepage]
• Variational Autoencoder for Anomaly Detection: A Comparative Study [2024][code]
• Revitalizing Reconstruction Models for Multi-class Anomaly Detection via Class-Aware Contrastive Learning [2024][code]

2.2.2 Generative Adversarial Networks (GANs)

• Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection [TIP 2023][code]
• Learning semantic context from normal samples for unsupervised anomaly detection [AAAI 2021]
• Anoseg: Anomaly segmentation network using self-supervised learning [2021]
• A Surface Defect Detection Method Based on Positive Samples [PRICAI 2018]
• Few-shot defect image generation via defect-aware feature manipulation [AAAI 2023][code]

2.2.3 Transformer

• VT-ADL: A vision transformer network for image anomaly detection and localization [ISIE 2021]
• ADTR: Anomaly Detection Transformer with Feature Reconstruction [2022]
• AnoViT: Unsupervised Anomaly Detection and Localization With Vision Transformer-Based Encoder-Decoder [2022]
• HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization [2022]
• Inpainting transformer for anomaly detection [ICIAP 2022]
• Masked Swin Transformer Unet for Industrial Anomaly Detection [2022]
• Masked Transformer for image Anomaly Localization [TII 2022]
• Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection [ICCV 2023][code]
• AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization [TASE 2024]
• Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection [TII 2024]
• Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection[2024][code]
• Multi-scale feature reconstruction network for industrial anomaly detection [KBS 2024][code]

2.2.4 Diffusion Model

• AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex Noise [CVPR Workshop 2022]
• Unsupervised Visual Defect Detection with Score-Based Generative Model[2022]
• DiffusionAD: Denoising Diffusion for Anomaly Detection [2023][code]
• Anomaly Detection with Conditioned Denoising Diffusion Models [2023]
• Unsupervised Surface Anomaly Detection with Diffusion Probabilistic Model [ICCV 2023]
• Removing Anomalies as Noises for Industrial Defect Localization [ICCV 2023]
• TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection [ECCV 2024][code]
• LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection [2023]
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [AAAI 2024][code]
• D3AD: Dynamic Denoising Diffusion Probabilistic Model for Anomaly Detection [2024]
• GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [ECCV 2024][code]
• Tackling Structural Hallucination in Image Translation with Local Diffusion [ECCV 2024 oral][code]

2.2.5 Others

• Anomaly Detection using Score-based Perturbation Resilience [ICCV 2023]

2.3 Supervised AD

More Normal samples With (Less Abnormal Samples or Weak Labels)

• Neural batch sampling with reinforcement learning for semi-supervised anomaly detection [ECCV 2020]
• Explainable Deep One-Class Classification [ICLR 2020]
• Attention guided anomaly localization in images [ECCV 2020]
• Mixed supervision for surface-defect detection: From weakly to fully supervised learning [2021]
• Explainable deep few-shot anomaly detection with deviation networks [2021][code]
• Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection [CVPR 2022][code]
• Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types[WACV 2023]
• Prototypical Residual Networks for Anomaly Detection and Localization [CVPR 2023][code]
• Efficient Anomaly Detection with Budget Annotation Using Semi-Supervised Residual Transformer [2023]
• Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection [CVPR 2024][code]
• Few-shot defect image generation via defect-aware feature manipulation [AAAI 2023][code]
• AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [AAAI 2024][code]
• BiaS: Incorporating Biased Knowledge to Boost Unsupervised Image Anomaly Localization [TSMC 2024]
• DMAD: Dual Memory Bank for Real-World Anomaly Detection [2024]
• AnomalousPatchCore: Exploring the Use of Anomalous Samples in Industrial Anomaly Detection [ECCVW 2024]
• SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection [ICIP 2024][code]

More Abnormal Samples

• Logit Inducing With Abnormality Capturing for Semi-Supervised Image Anomaly Detection [2022]
• An effective framework of automated visual surface defect detection for metal parts [2021]
• Interleaved Deep Artifacts-Aware Attention Mechanism for Concrete Structural Defect Classification [TIP 2021]
• Reference-based defect detection network [TIP 2021]
• Fabric defect detection using tactile information [ICRA 2021]
• A lightweight spatial and temporal multi-feature fusion network for defect detection [TIP 2020]
• SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection [Robotics and Computer-Integrated Manufacturing 2020]
• A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection [IEEE Access 2019]
• SDD-CNN: Small Data-Driven Convolution Neural Networks for Subtle Roller Defect Inspection [Applied Sciences 2019]
• Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types [CACIE 2018]
• Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning [2018]
• Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networks [Applied Sciences 2018]
• Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network [IFAC-PapersOnLine 2018]
• Domain adaptation for automatic OLED panel defect detection using adaptive support vector data description [IJCV 2017]
• Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network [TIM 2017]
• Deep Active Learning for Civil Infrastructure Defect Detection and Classification [Computing in civil engineering 2017]
• A fast and robust convolutional neural network-based defect detection model in product quality control [IJAMT 2017]
• Defects Detection Based on Deep Learning and Transfer Learning [Metallurgical & Mining Industry 2015]
• Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection [CIRP annals 2016]
• Decision Fusion Network with Perception Fine-tuning for Defect Classification [2023]
• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [2023]
• Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation [2023][code]
• MemoryMamba: Memory-Augmented State Space Model for Defect Recognition [2024]
• Supervised Anomaly Detection for Complex Industrial Images [2024][code]
• Small Object Few-shot Segmentation for Vision-based Industrial Inspection [2024][code]

3 Other Research Direction

3.1 Zero/Few-Shot AD

Zero-Shot AD

• Random Word Data Augmentation with CLIP for Zero-Shot Anomaly Detection [BMVC 2023]
• Zero-Shot Batch-Level Anomaly Detection [2023]
• Zero-shot versus Many-shot: Unsupervised Texture Anomaly Detection [WACV 2023]
• MAEDAY: MAE for few and zero shot AnomalY-Detection [2022]
• WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation [CVPR 2023] [unofficial code in AnomalyCLIP] [unofficial code in SAA] [unofficial code in mala-lab]
• Segment Any Anomaly without Training via Hybrid Prompt Regularization [2023] [code]
• Anomaly Detection in an Open World by a Neuro-symbolic Program on Zero-shot Symbols [IROS 2022 Workshop]
• AnoVL: Adapting Vision-Language Models for Unified Zero-shot Anomaly Localization [2023][code]
• CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection [2023]
• PromptAD: Zero-shot Anomaly Detection using Text Prompts [WACV 2024]
• High-Fidelity Zero-Shot Texture Anomaly Localization Using Feature Correspondence Analysis [WACV 2024]
• AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection [ICLR 2024][code]
• MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images[ICLR 2024][code]
• ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation [2023]
• APRIL-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 AD [CVPRW 2023][code]
• Model Selection of Zero-shot Anomaly Detectors in the Absence of Labeled Validation Data [2024]
• PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection [CVPR 2024][code]
• Do LLMs Understand Visual Anomalies? Uncovering LLM Capabilities in Zero-shot Anomaly Detection [2024]
• FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization [2024]
• Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection [2024]
• Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation [2024]
• SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection [2024]
• VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation [ECCV 2024][code]
• AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection [ECCV 2024][code]
• Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework [2024]
• PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection [NeurIPS 2024][code]
• VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection [2024]
• GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection [2024]
• Towards Zero-shot 3D Anomaly Localization [WACV 2025]

Few-Shot AD

• Learning unsupervised metaformer for anomaly detection [ICCV 2021]
• Registration based few-shot anomaly detection [ECCV 2022 oral][code]
• Same same but differnet: Semi-supervised defect detection with normalizing flows [(Distribution)WACV 2021]
• Towards total recall in industrial anomaly detection [(Memory bank)CVPR 2022]
• A hierarchical transformation-discriminating generative model for few shot anomaly detection [ICCV 2021]
• Anomaly detection of defect using energy of point pattern features within random finite set framework [2021]
• Optimizing PatchCore for Few/many-shot Anomaly Detection [2023][code]
• AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models [AAAI 2024][code][project page]
• FastRecon: Few-shot Industrial Anomaly Detection via Fast Feature Reconstruction [ICCV 2023][code]
• Produce Once, Utilize Twice for Anomaly Detection [2023]
• COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection [TIP2024]
• Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation [CVPR 2024][code]
• Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping [CVPR 2024]
• Dual-path Frequency Discriminators for Few-shot Anomaly Detection [2024]
• Few-shot Online Anomaly Detection and Segmentation [2024]
• FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks [CVPRW 2023][code]
• AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 [2024]
• Small Object Few-shot Segmentation for Vision-based Industrial Inspection [2024][code]
• Few-Shot Anomaly Detection via Category-Agnostic Registration Learning [2024][code]
• AnoPLe: Few-Shot Anomaly Detection via Bi-directional Prompt Learning with Only Normal Samples [2024][code]
• InCTRL: Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts [CVPR 2024][code]
• FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model[BMVC 2024][code]
• FOCT: Few-shot Industrial Anomaly Detection with Foreground-aware Online Conditional Transport [ACM MM 2024]
• UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection [2024][code]
• SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection [2024][code]
• CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP [2024][code]

3.2 Noisy AD

• Trustmae: A noise-resilient defect classification framework using memory-augmented auto-encoders with trust regions [WACV 2021]
• Self-Supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection [TMLR 2021]
• Data refinement for fully unsupervised visual inspection using pre-trained networks [2022]
• Latent Outlier Exposure for Anomaly Detection with Contaminated Data [ICML 2022]
• Deep one-class classification via interpolated gaussian descriptor [AAAI 2022 oral][code]
• SoftPatch: Unsupervised Anomaly Detection with Noisy Data [NeurIPS 2022][code]
• Inter-Realization Channels: Unsupervised Anomaly Detection Beyond One-Class Classification [ICCV 2023][code]
• M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising [2024]

3.3 Anomaly Synthetic

• Cutpaste: Self-supervised learning for anomaly detection and localization [(OCC)ICCV 2021][unofficial code]
• Draem-a discriminatively trained reconstruction embedding for surface anomaly detection [(Reconstruction AE)ICCV 2021][code]
• DSR: A dual subspace re-projection network for surface anomaly detection [ECCV 2022][code]
• Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization [ECCV 2022][code]
• MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities [(OCC)2022][unofficial code]
• A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection [IEEE Access 2019]
• Multistage GAN for fabric defect detection [2019]
• Gan-based defect synthesis for anomaly detection in fabrics [2020]
• Defect image sample generation with GAN for improving defect recognition [2020]
• Defective samples simulation through neural style transfer for automatic surface defect segment [2020]
• A simulation-based few samples learning method for surface defect segmentation [2020]
• Synthetic data augmentation for surface defect detection and classification using deep learning [2020]
• Defect Transfer GAN: Diverse Defect Synthesis for Data Augmentation [BMVC 2022]
• Defect-GAN: High-fidelity defect synthesis for automated defect inspection [2021]
• EID-GAN: Generative Adversarial Nets for Extremely Imbalanced Data Augmentation[TII 2022]
• Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection [2023]
• DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection [CVPR 2023][code]
• AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [AAAI 2024][code]
• RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection [CVPR 2024][code]
• Dual-path Frequency Discriminators for Few-shot Anomaly Detection [2024]
• A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation [2024][code]
• A Comprehensive Augmentation Framework for Anomaly Detection [AAAI 2024]
• CAGEN: Controllable Anomaly Generator using Diffusion Model [ICASSP 2024]
• AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion [2024][data]
• Few-shot defect image generation via defect-aware feature manipulation [AAAI 2023][code]
• A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization [ECCV 2024][code]
• SLSG: Industrial Image Anomaly Detection with Improved Feature Embeddings and One-Class Classification [PR 2024]
• Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection [ACM MM 2024]
• SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection [ICIP 2024][code]
• AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis [2024]

3.4 RGBD AD

• Anomaly detection in 3d point clouds using deep geometric descriptors [WACV 2022]
• Back to the feature: classical 3d features are (almost) all you need for 3D anomaly detection [2022][code]
• Anomaly Detection Requires Better Representations [2022]
• Asymmetric Student-Teacher Networks for Industrial Anomaly Detection [WACV 2022]
• Multimodal Industrial Anomaly Detection via Hybrid Fusion [CVPR 2023][code]
• Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection [2023][code]
• Image-Pointcloud Fusion based Anomaly Detection using PD-REAL Dataset [2023][data]
• Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network [CVPR 2024][code]
• Shape-Guided Dual-Memory Learning for 3D Anomaly Detection [ICML 2023]
• EasyNet: An Easy Network for 3D Industrial Anomaly Detection [ACM MM 2023]
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [2024]
• Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation [WACV 2024][code]
• Incremental Template Neighborhood Matching for 3D anomaly detection [Neurocomputing 2024]
• Keep DRÆMing: Discriminative 3D anomaly detection through anomaly simulation [PRL 2024]
• Rethinking Reverse Distillation for Multi-Modal Anomaly Detection [AAAI 2024]
• Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping [CVPR 2024]
• Cross-Modal Distillation in Industrial Anomaly Detection: Exploring Efficient Multi-Modal IAD [2024][code]
• M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising [2024]
• Towards Zero-shot 3D Anomaly Localization [WACV 2025]

3.5 3D AD

• Real3D-AD: A Dataset of Point Cloud Anomaly Detection [NeurIPS 2023][code]
• PointCore: Efficient Unsupervised Point Cloud Anomaly Detector Using Local-Global Features [2024]
• Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network [CVPR 2024][code]
• R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [ECCV 2024][homepage]
• Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning [ACM MM 2024][code]
• Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection [PR 2024] [code]
• Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework [2024][code]
• MulSen-AD: A Dataset and Benchmark for Multi-Sensor Anomaly Detection [2024][code]
• PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection [NeurIPS 2024][code]

3.6 Continual AD

• Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial Vision [2023]
• Towards Continual Adaptation in Industrial Anomaly Detection [ACM MM 2022]
• An Incremental Unified Framework for Small Defect Inspection [2023][code]
• Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt [AAAI 2024][code]

3.7 Uniform/Multi-Class AD

• A Unified Model for Multi-class Anomaly Detection [NeurIPS 2022] [code]
• OmniAL A unifiled CNN framework for unsupervised anomaly localization [CVPR 2023]
• SelFormaly: Towards Task-Agnostic Unified Anomaly Detection[2023]
• Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection [NeurIPS 2023][code]
• Removing Anomalies as Noises for Industrial Defect Localization [ICCV 2023]
• UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection [2023][code]
• MSTAD: A masked subspace-like transformer for multi-class anomaly detection [2023]
• LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection [2023]
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [AAAI 2024][code]
• Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly Detection [2023]
• Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization [2024]
• Unsupervised anomaly detection and localization with one model for all category [KBS 2024]
• Anomaly Detection by Adapting a pre-trained Vision Language Model [2024]
• DMAD: Dual Memory Bank for Real-World Anomaly Detection [2024]
• Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference [2024]
• Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection [ECCV 2024][code]
• Long-Tailed Anomaly Detection with Learnable Class Names [CVPR 2024][data split]
• MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection [NeurIPS 2024][code]
• Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [2024][code]
• Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection [2024]
• Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection [TII 2024]
• An Incremental Unified Framework for Small Defect Inspection [ECCV2024][code]
• Learning Multi-view Anomaly Detection [2024]
• Revitalizing Reconstruction Models for Multi-class Anomaly Detection via Class-Aware Contrastive Learning [2024][code]

3.8 Logical AD

• Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization [IJCV 2022]
• Set Features for Fine-grained Anomaly Detection[2023] [code]
• EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies [WACV 2024]
• Contextual Affinity Distillation for Image Anomaly Detection [WACV 2024]
• REB: Reducing Biases in Representation for Industrial Anomaly Detection [2023][code]
• Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection [TCSVT 2023][code]
• Template-guided Hierarchical Feature Restoration for Anomaly Detection [ICCV 2023]
• Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection [AAAI 2024][code]
• Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection [AAAI 2024]
• PUAD: Frustratingly Simple Method for Robust Anomaly Detection [2024]
• AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion [2024][data]
• Supervised Anomaly Detection for Complex Industrial Images [2024][code]
• SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection [2024]
• SLSG: Industrial Image Anomaly Detection with Improved Feature Embeddings and One-Class Classification [PR 2024]
• Unsupervised Component Segmentation for Logical Anomaly Detection [2024] [code]
• LogiCode: an LLM-Driven Framework for Logical Anomaly Detection [2024]
• CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection [BMVC 2024][code]
• Revisiting Deep Feature Reconstruction for Logical and Structural Industrial Anomaly Detection[TMLR 2024][code]

Other settings

TTT binary segmentation

• Test Time Training for Industrial Anomaly Segmentation [2024]

MoE with TTA

• Adapted-MoE: Mixture of Experts with Test-Time Adaption for Anomaly Detection[2024][[code coming soon]]

Adversary Attack

• Adversarially Robust Industrial Anomaly Detection Through Diffusion Model [2024]

Defect Classification

• AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios [2024][code coming soon]

4 Dataset

• (NEU surface defect dataset)A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects [2013] [data]
• (Steel tube dataset)Deep learning based steel pipe weld defect detection [2021] [data]
• (Steel defect dataset)Severstal: Steel Defect Detection [data 2019]
• (NanoTwice)Defect detection in SEM images of nanofibrous materials [TII 2016] [data]
• (GDXray)GDXray: The database of X-ray images for nondestructive testing [2015] [data]
• (DEEP PCB)Online PCB defect detector on a new PCB defect dataset [2019] [data]
• (PCBA-defect) A PCB Dataset for Defects Detection and Classification [2019][data]
• (CPLID) Insulator Data Set - Chinese Power Line Insulator Dataset [data]
• (Fabric dataset)Fabric inspection based on the Elo rating method [PR 2016]
• (KolektorSDD)Segmentation-based deep-learning approach for surface-defect detection [Journal of Intelligent Manufacturing] [data]
• (KolektorSDD2)Mixed supervision for surface-defect detection: From weakly to fully supervised learning [Computers in Industry 2021] [data]
• SensumSODF-dataset: Detection of surface defects on pharmaceutical solid oral dosage forms with convolutional neural networks[Neural Computing and Applications 2021][data]
• (RSDD)A hierarchical extractor-based visual rail surface inspection system [2017]
• (Eyecandies)The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization [ACCV 2022] [data]
• (MVTec AD)MVTec AD: A comprehensive real-world dataset for unsupervised anomaly detection [CVPR 2019] [IJCV 2021] [data]✨✨✨
• (MVTec 3D-AD)The mvtec 3d-ad dataset for unsupervised 3d anomaly detection and localization [VISAPP 2021] [data]✨✨
• (MVTec LOCO-AD)Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization [IJCV 2022] [data]✨✨✨
• (MPDD)Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions [ICUMT 2021] [data]
• (MPDD2)Anomaly detection for real-world industrial applications: benchmarking recent self-supervised and pretrained methods [ICUMT 2022] [data]
• (BTAD)VT-ADL: A vision transformer network for image anomaly detection and localization [2021] [data]
• (VisA)SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation [ECCV 2022] [data]✨✨✨
• (MTD)Surface defect saliency of magnetic tile [2020] [data]
• (DAGM)DAGM dataset [data 2007]
• (MIAD)Miad:A maintenance inspection dataset for unsupervised anomaly detection [2022] [data]✨✨
• CVPR 1st workshop on Vision-based InduStrial InspectiON [homepage] [data]
• (SSGD)SSGD: A smartphone screen glass dataset for defect detection [2023][github page]
• (AeBAD)Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstruction [2023] [data]
• VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON [2023] [data]✨✨✨
• PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection [NeurIPS 2023]
• PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation [2023][data]✨✨
• Real3D-AD: A Dataset of Point Cloud Anomaly Detection [NeurIPS 2023][data]✨✨✨
• InsPLAD: A Dataset and Benchmark for Power Line Asset Inspection in UAV Images [IJRS 2023][data]
• Image-Pointcloud Fusion based Anomaly Detection using PD-REAL Dataset [2023][data]
• CrashCar101: Procedural Generation for Damage Assessment [WACV 2024][data]
• Defect Spectrum: A Granular Look of Large-Scale Defect Datasets with Rich Semantics [ECCV 2024][data]
• (DTD-Synthetic) Zero-shot versus Many-shot: Unsupervised Texture Anomaly Detection [WACV 2023][data]
• Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network [CVPR 2024][data]
• Real-IAD: A Real-World Multi-view Dataset for Benchmarking Versatile Industrial Anomaly Detection [CVPR 2024][code][data]✨✨✨
• Catenary Insulator Defects Detection: A Dataset and an Unsupervised Baseline [TIM 2024][code]
• IPAD: Industrial Process Anomaly Detection Dataset [2024][data]
• MVTec-Caption: AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion [2024][data]
• Supervised Anomaly Detection for Complex Industrial Images [2024][data]
• PeanutAD: A Real-World Dataset for Anomaly Detection in Agricultural Product Processing Line [2024][data]
• The Woven Fabric Defect Detection (WFDD) dataset [2024][data]
• Texture-AD: An Anomaly Detection Dataset and Benchmark for Real Algorithm Development[2024][data]
• MulSen-AD: A Dataset and Benchmark for Multi-Sensor Anomaly Detection [2024][data]
• CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset [NeurIPS 2024][data]
• RAD: A Dataset and Benchmark for Real-Life Anomaly Detection with Robotic Observations [2024][data]
• AD3: Introducing a score for Anomaly Detection Dataset Difficulty assessment using VIADUCT dataset [ECCV 2024]
• MMAD: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection [2024] [data]
• MANTA: A Large-Scale Multi-View and Visual-Text Anomaly Detection Dataset for Tiny Objects [2024][data]

BibTex Citation

If you find this paper and repository useful, please cite our paper☺️.

@article{liu2024deep,
  title={Deep industrial image anomaly detection: A survey},
  author={Liu, Jiaqi and Xie, Guoyang and Wang, Jinbao and Li, Shangnian and Wang, Chengjie and Zheng, Feng and Jin, Yaochu},
  journal={Machine Intelligence Research},
  volume={21},
  number={1},
  pages={104--135},
  year={2024},
  publisher={Springer}
}

@article{xie2024iad,
  title={Im-iad: Industrial image anomaly detection benchmark in manufacturing},
  author={Xie, Guoyang and Wang, Jinbao and Liu, Jiaqi and Lyu, Jiayi and Liu, Yong and Wang, Chengjie and Zheng, Feng and Jin, Yaochu},
  journal={IEEE Transactions on Cybernetics},
  year={2024},
  publisher={IEEE}
}

@article{jiang2022survey,
  title={A survey of visual sensory anomaly detection},
  author={Jiang, Xi and Xie, Guoyang and Wang, Jinbao and Liu, Yong and Wang, Chengjie and Zheng, Feng and Jin, Yaochu},
  journal={arXiv preprint arXiv:2202.07006},
  year={2022}
}

Star History