| A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization | ✓ Link | 99.9 | 96.8 | 99.3 | | | GLASS | 2024-07-12 |
| UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection | ✓ Link | 99.90 | 96.00 | 98.81 | | | UniNet | 2025-02-28 |
| Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection | ✓ Link | 99.8 | 97.3 | 98.6 | | | PBAS | 2024-12-23 |
| Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection | ✓ Link | 99.8 | 96.4 | 99 | | | HETMM | 2023-03-28 |
| Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection | ✓ Link | 99.8 | 95.6 | 98.6 | 72.1 | | INP-Fomer ViT-L (model-unified multi-class) | 2025-03-04 |
| Anomaly Detection with Conditioned Denoising Diffusion Models | ✓ Link | 99.8 | | 98.1 | | | DDAD | 2023-05-25 |
| EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies | ✓ Link | 99.8 | | | | 269 | EfficientAD (early stopping) | 2023-03-25 |
| Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection | ✓ Link | 99.77 | 95.09 | 98.54 | 70.53 | | Dinomaly ViT-L (model-unified multi-class) | 2024-05-23 |
| ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection | ✓ Link | 99.72 | | 99.2 | | | ReConPatch Ensemble (+RefineNet) | 2023-05-26 |
| ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection | ✓ Link | 99.71 | | 98.62 | | | ReConPatch WRN-50 (+RefineNet) | 2023-05-26 |
| Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization | | 99.7 | 97.8 | 99.2 | 82.9 | | ADClick | 2024-07-03 |
| Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval | ✓ Link | 99.7 | 97.8 | 99.2 | 82.7 | 113 | CPR | 2023-08-13 |
| Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval | ✓ Link | 99.7 | 97.7 | 99.2 | 82.3 | 245 | CPR-fast | 2023-08-13 |
| MSFlow: Multi-Scale Flow-based Framework for Unsupervised Anomaly Detection | ✓ Link | 99.7 | 97.1 | 98.8 | | | MSFlow | 2023-08-29 |
| Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection | ✓ Link | 99.7 | | 98.4 | | | CRAS | 2025-05-23 |
| PNI : Industrial Anomaly Detection using Position and Neighborhood Information | ✓ Link | 99.63 | 96.55 | 99.06 | | | PNI Ensemble | 2022-11-22 |
| ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection | ✓ Link | 99.62 | | 98.53 | | | ReConPatch WRN-101 | 2023-05-26 |
| Industrial Anomaly Detection and Localization Using Weakly-Supervised Residual Transformers | | 99.6 | 97.6 | 99.3 | 83.0 | 25.2 | WeakREST-Un | 2023-06-06 |
| Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection | ✓ Link | 99.60 | 94.79 | 98.35 | 69.29 | | Dinomaly ViT-B (model-unified multi-class) | 2024-05-23 |
| Towards Total Recall in Industrial Anomaly Detection | ✓ Link | 99.6 | 93.5 | 98.2 | | 5.88 | PatchCore Large | 2021-06-15 |
| RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection | ✓ Link | 99.6 | 93.0 | 99.0 | | | RealNet | 2024-03-09 |
| Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection | ✓ Link | 99.6 | | 98.2 | | | RememberingNormality | 2023-01-01 |
| SimpleNet: A Simple Network for Image Anomaly Detection and Localization | ✓ Link | 99.6 | | 98.1 | | 77(FP32 on 3080ti) | SimpleNet | 2023-03-27 |
| PNI : Industrial Anomaly Detection using Position and Neighborhood Information | ✓ Link | 99.56 | 96.05 | 98.98 | | | PNI | 2022-11-22 |
| MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities | ✓ Link | 99.56 | | 98.84 | | 31.3 | MemSeg | 2022-05-02 |
| ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection | ✓ Link | 99.56 | | 98.18 | | | ReConPatch WRN-50 | 2023-05-26 |
| []() | | 99.5 | 95.2 | 98.4 | | | ReContrast | |
| AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 | ✓ Link | 99.5 | 95 | 98.2 | | | AnomalyDINO-S (full-shot) | 2024-05-23 |
| Produce Once, Utilize Twice for Anomaly Detection | | 99.5 | | 98.8 | | | POUTA | 2023-12-20 |
| Diversity-Measurable Anomaly Detection | ✓ Link | 99.5 | | 98.2 | | | DMAD | 2023-03-09 |
| []() | | 99.5 | | 96.88 | | | GRD-Net
(Partial) | |
| Revisiting Reverse Distillation for Anomaly Detection | ✓ Link | 99.44 | 94.99 | 98.25 | | | Reverse Distillation ++ | 2023-01-01 |
| Continuous Memory Representation for Anomaly Detection | ✓ Link | 99.4 | 97.9 | | | | CRAD | 2024-02-28 |
| Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval | ✓ Link | 99.4 | 97.3 | 99.0 | 80.6 | 478 | CPR-faster | 2023-08-13 |
| TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection | ✓ Link | 99.4 | 95.3 | | | | TransFusion | 2023-11-16 |
| FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows | ✓ Link | 99.4 | | 98.5 | | 21.8 | Fastflow | 2021-11-15 |
| AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection | | 99.4 | | 98.5 | | | CFLOW-AD+AltUB | 2022-10-26 |
| N-pad : Neighboring Pixel-based Industrial Anomaly Detection | | 99.37 | 95.1 | 98.75 | | | N-pad | 2022-10-17 |
| GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection | ✓ Link | 99.3 | 95.3 | 98.6 | 70.9 | | GLAD | 2024-06-11 |
| CFA: Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization | ✓ Link | 99.3 | | 98.2 | | | CFA | 2022-06-09 |
| Unlocking the Potential of Reverse Distillation for Anomaly Detection | ✓ Link | 99.2 | 96.3 | 99.0 | 72.4 | | URD | 2024-12-10 |
| Template-guided Hierarchical Feature Restoration for Anomaly Detection | | 99.2 | 95.0 | 98.2 | | | THFR | 2023-01-01 |
| Towards Total Recall in Industrial Anomaly Detection | ✓ Link | 99.2 | | 98.4 | | | PatchCore | 2021-06-15 |
| Asymmetric Student-Teacher Networks for Industrial Anomaly Detection | ✓ Link | 99.2 | | 95.0 | | | AST | 2022-10-14 |
| EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies | ✓ Link | 99.1 | 93.5 | | | 269 | EfficientAD-M | 2023-03-25 |
| Reconstruction-Free Anomaly Detection with Diffusion Models via Direct Latent Likelihood Evaluation | ✓ Link | 99.1 | | | | 11 | InversionAD | 2025-04-08 |
| FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection | ✓ Link | 99 | | 98 | | 44.1 | FAPM | 2022-11-14 |
| Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection | ✓ Link | 98.9 | | 97.2 | 69.9 | | DRAEM+SSPCAB | 2021-11-17 |
| Anomaly Detection Using Normalizing Flow-Based Density Estimation and Synthetic Defect Classification | ✓ Link | 98.85 | 96.01 | 98.74 | 74.32 | | AD-CLSCNFs | 2024-05-28 |
| Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection | | 98.7 | 95.1 | 98.5 | | | RSTPM | 2022-10-14 |
| EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies | ✓ Link | 98.7 | 93.1 | | 65.9 | 614 | EfficientAD-S | 2023-03-25 |
| Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection | | 98.7 | | 97.3 | | | GRAD | 2023-12-26 |
| Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection | ✓ Link | 98.7 | | 97.2 | | | DRAEM+SSMCTB | 2022-09-25 |
| Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection | ✓ Link | 98.7 | | | | | CS-Flow | 2021-10-06 |
| FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection | ✓ Link | 98.6 | 94.0 | 98.2 | | | FAIR | 2023-09-13 |
| DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection | ✓ Link | 98.6 | | 97.9 | 75.8 | | DeSTSeg | 2022-11-21 |
| Anomaly Detection via Reverse Distillation from One-Class Embedding | ✓ Link | 98.5 | 93.9 | 97.8 | | | Reverse Distillation | 2022-01-26 |
| Industrial Anomaly Detection with Domain Shift: A Real-world Dataset and Masked Multi-scale Reconstruction | ✓ Link | 98.4 | 92.6 | 97.2 | | | MMR | 2023-04-05 |
| SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection | ✓ Link | 98.4 | 91.1 | | | 107 (Tesla V100S) | SuperSimpleNet | 2024-08-06 |
| SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection | | 98.4 | | 98.5 | | | SAM-LAD | 2024-06-02 |
| Multi-scale feature reconstruction network for industrial anomaly detection | ✓ Link | 98.4 | | | | | MSFR | 2024-10-23 |
| Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection | ✓ Link | 98.3 | | | | | OCR-GAN | 2022-03-01 |
| CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows | ✓ Link | 98.26 | 94.6 | 98.62 | | 27 | CFLOW-AD | 2021-07-27 |
| A Probabilistic Transformation of Distance-Based Outliers | ✓ Link | 98.2 | | 97.6 | | | ProbabilisticPatchCore | 2023-05-16 |
| DSR -- A dual subspace re-projection network for surface anomaly detection | ✓ Link | 98.2 | | | 70.2 | | DSR | 2022-08-02 |
| Multi-Scale Patch-Based Representation Learning for Image Anomaly Detection and Segmentation | | 98.1 | 95.5 | 98.1 | | | MSPBA | 2022-10-23 |
| Two-stage coarse-to-fine image anomaly segmentation and detection model | ✓ Link | 98.0 | | 98.2 | 74.6 | 142 | TASAD | 2023-09-19 |
| DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection | ✓ Link | 98.0 | | 97.3 | 68.4 | | DRAEM | 2021-08-17 |
| Anomaly Detection via Self-organizing Map | ✓ Link | 97.9 | 93.3 | 97.8 | | | SOMAD | 2021-07-21 |
| PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization | ✓ Link | 97.9 | | | | | PaDiM | 2020-11-17 |
| MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images | ✓ Link | 97.8 | 93.8 | 97.3 | 62.7 | | MuSc (zero-shot) | 2024-01-30 |
| Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection | ✓ Link | 97.8 | 92.1 | 97.7 | | | EdgRec | 2022-10-26 |
| AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 | ✓ Link | 97.7 | 93.4 | 97.2 | | | AnomalyDINO-S (4-shot) | 2024-05-23 |
| Focus Your Distribution: Coarse-to-Fine Non-Contrastive Learning for Anomaly Detection and Localization | | 97.7 | | 98.2 | | | FYD | 2021-10-09 |
| Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection | ✓ Link | 97.7 | | 96.7 | | | NSA+SSMCTB | 2022-09-25 |
| ISSTAD: Incremental Self-Supervised Learning Based on Transformer for Anomaly Detection and Localization | ✓ Link | 97.6 | | 96.1 | | | ISSTAD | 2023-03-30 |
| Unsupervised Image Anomaly Detection and Segmentation Based on Pre-trained Feature Mapping | ✓ Link | 97.5 | 93.0 | 97.3 | | | PFM | 2021-08-06 |
| Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization | ✓ Link | 97.2 | 91.0 | 96.3 | | | NSA | 2021-09-30 |
| AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 | ✓ Link | 96.9 | 93.1 | 97.0 | | | AnomalyDINO-S (2-shot) | 2024-05-23 |
| AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2 | ✓ Link | 96.6 | 92.7 | 96.8 | | | AnomalyDINO-S (1-shot) | 2024-05-23 |
| Deep Feature Selection for Anomaly Detection Based on Pretrained Network and Gaussian Discriminative Analysis | ✓ Link | 96.6 | | | | | Gaussian-AD+DFS | 2022-09-12 |
| Exploring Dual Model Knowledge Distillation for Anomaly Detection | | 96.2 | | | | | DualModel | 2023-06-27 |
| Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection | ✓ Link | 96.1 | | | | | CutPaste+SSPCAB | 2021-11-17 |
| CutPaste: Self-Supervised Learning for Anomaly Detection and Localization | ✓ Link | 96.1 | | | | | CutPaste (ensemble) | 2021-04-08 |
| AnoSeg: Anomaly Segmentation Network Using Self-Supervised Learning | | 96 | | 97 | | | AnoSeg | 2021-10-07 |
| SCL-VI: Self-supervised Context Learning for Visual Inspection of Industrial Defects | ✓ Link | 95.81 | | 96.76 | | | SCL-VI | 2023-11-11 |
| Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection | ✓ Link | 95.8 | | | | | Gaussian-AD | 2020-05-28 |
| Student-Teacher Feature Pyramid Matching for Anomaly Detection | ✓ Link | 95.5 | | 97.0 | | | STPM | 2021-03-07 |
| Towards Total Recall in Industrial Anomaly Detection | ✓ Link | 95.4 | | | | | PatchCore(16shot) | 2021-06-15 |
| PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization | ✓ Link | 95.3 | | 97.5 | | 4.4 | PaDiM-WR50-Rd550 | 2020-11-17 |
| WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation | ✓ Link | 95.2 | 89 | | | | WinCLIP+ (4-shot) | 2023-03-26 |
| CutPaste: Self-Supervised Learning for Anomaly Detection and Localization | ✓ Link | 95.2 | | 88.3 | | | CutPaste (Image level detector) | 2021-04-08 |
| Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework | ✓ Link | 95.1 | | | | | RFS Energy | 2021-08-27 |
| Inpainting Transformer for Anomaly Detection | ✓ Link | 95.0 | | 96.6 | | | InTra | 2021-04-28 |
| Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows | ✓ Link | 94.9 | | | | 2 | DifferNet | 2020-08-28 |
| WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation | ✓ Link | 94.4 | 88.4 | | | | WinCLIP+ (2-shot) | 2023-03-26 |
| Excision And Recovery: Visual Defect Obfuscation Based Self-Supervised Anomaly Detection Strategy | | 94.2 | | | | | EAR | 2023-10-06 |
| DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation | ✓ Link | 93.8 | | 95.5 | | 20 | DFR | 2020-12-13 |
| Deep One-Class Classification via Interpolated Gaussian Descriptor | ✓ Link | 93.4 | | 93.0 | | | IGD (pre-trained SSL) | 2021-01-25 |
| Deep One-Class Classification via Interpolated Gaussian Descriptor | ✓ Link | 93.4 | | | | | IGD | 2021-01-25 |
| WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation | ✓ Link | 93.1 | 87.1 | | | | WinCLIP+ (1-shot) | 2023-03-26 |
| Industrial Image Anomaly Localization Based on Gaussian Clustering of Pretrained Feature | ✓ Link | 93.1 | | 96.86 | | | GCPF | 2021-01-06 |
| PEDENet: Image Anomaly Localization via Patch Embedding and Density Estimation | | 92.8 | | 95.9 | | | PEDENet | 2021-10-29 |
| Registration based Few-Shot Anomaly Detection | ✓ Link | 92.7 | | 96.6 | | | RegAD (16 shot) | 2022-07-15 |
| Deep One-Class Classification via Interpolated Gaussian Descriptor | ✓ Link | 92.6 | | 91 | | | IGD (pre-trained ImageNet) | 2021-01-25 |
| Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation | ✓ Link | 92.1 | | 95.7 | | 2.1 | Patch-SVDD | 2020-06-29 |
| WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation | ✓ Link | 91.8 | 64.6 | | | | WinCLIP (0-shot) | 2023-03-26 |
| Reconstruction by Inpainting for Visual Anomaly Detection | ✓ Link | 91.7 | | 94.2 | | | RIAD | 2020-10-17 |
| AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection | ✓ Link | 91.5 | 81.4 | 91.1 | | | AnomalyCLIP | 2023-10-29 |
| Registration based Few-Shot Anomaly Detection | ✓ Link | 91.2 | | 96.7 | | | RegAD (8 shot) | 2022-07-15 |
| Unsupervised Two-Stage Anomaly Detection | | 90 | | | | | UTAD | 2021-03-22 |
| Can I trust my anomaly detection system? A case study based on explainable AI | ✓ Link | 90 | | | | | VAE-GAN | 2024-07-29 |
| AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection | ✓ Link | 89.2 | | 88.7 | | | AdaCLIP | 2024-07-22 |
| Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework | ✓ Link | 89.02 | | | | | RFS Energy (16 shot) | 2021-08-27 |
| Registration based Few-Shot Anomaly Detection | ✓ Link | 88.2 | | 95.8 | | | RegAD (4 shot) | 2022-07-15 |
| MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection | ✓ Link | 87.5 | | | | | MOCCA | 2020-12-09 |
| Mean-Shifted Contrastive Loss for Anomaly Detection | ✓ Link | 87.2 | | | | | Mean-Shifted Contrastive Loss | 2021-06-07 |
| Learning and Evaluating Representations for Deep One-class Classification | ✓ Link | 86.5 | | 90.4 | | | DisAug CLR | 2020-11-04 |
| Learning and Evaluating Representations for Deep One-class Classification | ✓ Link | 86.3 | | 93 | | | RotNet (MLP Head) | 2020-11-04 |
| 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 | ✓ Link | 86.1 | 44.0 | 87.6 | 40.8 | | APRIL-GAN（zero-shot） | 2023-05-27 |
| Zero-Shot Anomaly Detection via Batch Normalization | ✓ Link | 85.8 | 72.7 | 92.5 | 38.9 | | ACR (zero-shot) | 2023-02-15 |
| Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework | ✓ Link | 85.61 | | | | | RFS Energy (1 shot) | 2021-08-27 |
| Sub-Image Anomaly Detection with Deep Pyramid Correspondences | ✓ Link | 85.5 | | 96.5 | | 1.5 | SPADE | 2020-05-05 |
| Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization | ✓ Link | | 96.50 | 98.70 | | 79.6 (exclude data inputting time), 18.7 (contain data inputting time) | CDO | 2023-02-17 |
| PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow | | | 96.5 | 97.1 | | | PyramidFlow (Res18) | 2023-03-05 |
| Position Encoding Enhanced Feature Mapping for Image Anomaly Detection | ✓ Link | | 95.52 | 98.30 | | | PEFM | 2022-06-06 |
| PyramidFlow: High-Resolution Defect Contrastive Localization using Pyramid Normalizing Flow | | | 94.5 | 96.0 | | | PyramidFlow (FNF) | 2023-03-05 |
| Informative knowledge distillation for image anomaly segmentation | ✓ Link | | 92.55 | 97.81 | | | IKD | 2022-07-19 |
| Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings | ✓ Link | | 91.4 | | 45.5 | | Student–Teacher AD (Multiscale) | 2019-11-06 |
| Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings | ✓ Link | | 90.0 | | | | Student–Teacher AD (p=33) | 2019-11-06 |
| VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation | ✓ Link | | 87.3 | 92.0 | 49.4 | | VCP-CLIP | 2024-07-17 |
| Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings | ✓ Link | | 85.7 | | | | Student–Teacher AD (p=65) | 2019-11-06 |
| AltUB: Alternating Training Method to Update Base Distribution of Normalizing Flow for Anomaly Detection | | | | 98.83 | | | FastFlow+AltUB | 2022-10-26 |
| ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection | ✓ Link | | | 98.67 | | | ReConPatch Ensemble | 2023-05-26 |
| Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation | ✓ Link | | | 98.2 | | | Semi-orthogonal | 2021-05-31 |
| PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization | ✓ Link | | | 96.7 | | | PaDiM-R18-Rd100 | 2020-11-17 |
| CutPaste: Self-Supervised Learning for Anomaly Detection and Localization | ✓ Link | | | 96.0 | | | CutPaste (Patch level detector) | 2021-04-08 |
| Anomaly localization by modeling perceptual features | ✓ Link | | | 95.3 | | | FAVAE | 2020-08-12 |
| Explainable Deep One-Class Classification | ✓ Link | | | 94 | | | FCDD (semi-supervised) | 2020-07-03 |
| Attention Guided Anomaly Localization in Images | | | | 93 | | | CAVGA-R (weakly-supervised) | 2019-11-19 |
| Attention Guided Anomaly Localization in Images | | | | 92 | | | CAVGA-D (weakly-supervised) | 2019-11-19 |
| Iterative energy-based projection on a normal data manifold for anomaly localization | ✓ Link | | | 89.2 | | | VAE-grad | 2020-02-10 |
| Attention Guided Anomaly Localization in Images | | | | 89 | | | CAVGA-R (unsupervised) | 2019-11-19 |
| Explainable Deep One-Class Classification | ✓ Link | | | 88 | | | FCDD (unsupervised) | 2020-07-03 |
| Attention Guided Anomaly Localization in Images | | | | 85 | | | CAVGA-D (unsupervised) | 2019-11-19 |
| Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval | ✓ Link | | | | | 1016 | CPR-faster(TensorRT) | 2023-08-13 |
| Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval | ✓ Link | | | | | 362 | CPR-fast(TensorRT) | 2023-08-13 |
| Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval | ✓ Link | | | | | 130 | CPR(TensorRT) | 2023-08-13 |