| CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection | ✓ Link | 95.3 | 96.7 | 94.0 | | CSAD | 2024-08-28 |
| Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection | ✓ Link | 94.9 | 98.1 | 91.6 | | PSAD | 2023-12-21 |
| PUAD: Frustratingly Simple Method for Robust Anomaly Detection | ✓ Link | 94.4 | 93.7 | 95.9 | | PUAD-M | 2024-02-23 |
| Set Features for Anomaly Detection | ✓ Link | 94.2 | 95.8 | 94.2 | | SINBAD+EfficientAD | 2023-11-24 |
| PUAD: Frustratingly Simple Method for Robust Anomaly Detection | ✓ Link | 93.1 | 92.0 | 94.1 | | PUAD-S | 2024-02-23 |
| EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies | ✓ Link | 90.7 | 86.8 | 94.7 | 79.8 | EfficientAD-M | 2023-03-25 |
| SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection | | 90.7 | | | 83.2 | SAM-LAD | 2024-06-02 |
| SLSG: Industrial Image Anomaly Detection by Learning Better Feature Embeddings and One-Class Classification | | 90.3 | 89.6 | 91.4 | 67.3 | SLSG | 2023-04-30 |
| Component-aware anomaly detection framework for adjustable and logical industrial visual inspection | ✓ Link | 90.1 | 89.4 | 90.9 | | ComAD+PatchCore | 2023-05-15 |
| EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies | ✓ Link | 90.0 | 85.8 | 94.1 | 77.8 | EfficientAD-S | 2023-03-25 |
| Component-aware anomaly detection framework for adjustable and logical industrial visual inspection | ✓ Link | 89.8 | 90.1 | 89.4 | | ComAD+AST | 2023-05-15 |
| Set Features for Anomaly Detection | ✓ Link | 88.3 | 91.2 | 85.5 | | SINBAD Ens | 2023-11-24 |
| Component-aware anomaly detection framework for adjustable and logical industrial visual inspection | ✓ Link | 88.2 | 87.5 | 88.8 | | ComAD+RD4AD | 2023-05-15 |
| Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection | ✓ Link | 88.1 | 83.2 | 92.9 | | HETMM | 2023-03-28 |
| Component-aware anomaly detection framework for adjustable and logical industrial visual inspection | ✓ Link | 87.9 | 85.9 | 89.9 | | ComAD+DRAEM | 2023-05-15 |
| Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection | | 87.5 | | | | GRAD | 2023-12-26 |
| Set Features for Fine-grained Anomaly Detection | ✓ Link | 86.8 | 88.9 | 84.7 | | SINBAD | 2023-02-23 |
| Template-guided Hierarchical Feature Restoration for Anomaly Detection | | 86.0 | 85.2 | 86.7 | 74.1 | THFR | 2023-01-01 |
| LADMIM: Logical Anomaly Detection with Masked Image Modeling in Discrete Latent Space | | 86.0 | 83.1 | 90.3 | | LADMIM | 2024-10-14 |
| Contextual Affinity Distillation for Image Anomaly Detection | | 84.0 | 81.2 | 86.9 | 73.0 | DSKD | 2023-07-06 |
| Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow | ✓ Link | 83.7 | 79.2 | 88.2 | 67.4 | DADF | 2023-03-31 |
| Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization | | 83.3 | 86.0 | 80.6 | 70.1 | GCAD | 2022-02-22 |
| Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection | | 83.1 | 82.4 | 83.8 | 70.3 | GLCF | 2023-03-10 |
| DSR -- A dual subspace re-projection network for surface anomaly detection | ✓ Link | 82.6 | 75.0 | 90.2 | 58.5 | DSR | 2022-08-02 |
| Component-aware anomaly detection framework for adjustable and logical industrial visual inspection | ✓ Link | 81.2 | 87.7 | 74.6 | | ComAD | 2023-05-15 |
| Towards Total Recall in Industrial Anomaly Detection | ✓ Link | 80.3 | 75.8 | | 39.7 | PatchCore | 2021-06-15 |
| Towards Total Recall in Industrial Anomaly Detection | ✓ Link | 79.4 | 71.0 | 87.7 | 36.5 | PatchCore Ensemble | 2021-06-15 |
| FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows | ✓ Link | 79.2 | 75.5 | 82.9 | 56.8 | FastFlow | 2021-11-15 |
| Anomaly Detection via Reverse Distillation from One-Class Embedding | ✓ Link | 78.7 | 69.4 | 88.0 | 63.7 | RD4AD | 2022-01-26 |
| SimpleNet: A Simple Network for Image Anomaly Detection and Localization | ✓ Link | 77.6 | 71.5 | 83.7 | 36.3 | SimpleNet | 2023-03-27 |
| Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings | ✓ Link | 77.3 | 66.4 | 88.3 | | Student-Teacher | 2019-11-06 |
| MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images | ✓ Link | 75.9 | 67.47 | 84.3 | 63.04 | MuSc (zero-shot) | 2024-01-30 |
| DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection | ✓ Link | 73.6 | 72.8 | 74.4 | 42.6 | DRAEM | 2021-08-17 |
| Sub-Image Anomaly Detection with Deep Pyramid Correspondences | ✓ Link | 68.9 | 70.9 | 66.8 | 45.1 | SPADE | 2020-05-05 |
| Learning Memory-guided Normality for Anomaly Detection | ✓ Link | 65.1 | 60.0 | 70.2 | 33.9 | MNAD | 2020-03-30 |
| f-AnoGAN: Fast Unsupervised Anomaly Detection with Generative Adversarial Networks | ✓ Link | 64.2 | 65.8 | 62.7 | 33.4 | f-AnoGAN | 2019-01-30 |
| Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization | | 57.7 | 56.5 | 58.9 | 22.5 | Variation Model | 2022-02-22 |
| Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and Localization | | 57.3 | 58.1 | 56.5 | 37.8 | L2AE | 2022-02-22 |
| Auto-Encoding Variational Bayes | ✓ Link | 54.3 | 53.8 | 54.8 | 38.2 | VAE | 2013-12-20 |
| Asymmetric Student-Teacher Networks for Industrial Anomaly Detection | ✓ Link | | 79.7 | 87.1 | 42.7 | AST | 2022-10-14 |