Image Models#
Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
Boosting Patch-based Few-shot Anomaly Detection with DINOv2
Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization
Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping
Real-Time Unsupervised Anomaly Detection via Conditional Normalizing Flows
Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection
Deep Feature Kernel Density Estimation
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
Dinomaly: The Less Is More Philosophy in Unsupervised Anomaly Detection
DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection
DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection
FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
FRE: A Fast Method For Anomaly Detection And Segmentation
GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
Anomaly Detection Across Domains by Attending to Distorted Features
Learning to Be a Transformer to Pinpoint Anomalies
PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization
Towards Total Recall in Industrial Anomaly Detection
PatchFlow: Leveraging a Flow-Based Model with Patch Features
Anomaly Detection via Reverse Distillation from One-Class Embedding.
Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection
SuperSimpleNet: A Unified Surface Defect Detection Model for all Supervision Regimes
U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold
UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection
VLM-AD: Vision-Language Model for Anomaly Detection
WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation