Image Models

Image Models#

CFA

Coupled-hypersphere-based Feature Adaptation for Target-Oriented Anomaly Localization

C-Flow

Real-Time Unsupervised Anomaly Detection via Conditional Normalizing Flows

CS-Flow

Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection

DFKDE

Deep Feature Kernel Density Estimation

DFM

Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection

DRAEM

DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection

DSR

DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection

Efficient AD

EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies

FastFlow

FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows

GANomaly

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training

PaDiM

PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization

Patchcore

Towards Total Recall in Industrial Anomaly Detection

Reverse Distillation

Anomaly Detection via Reverse Distillation from One-Class Embedding.

R-KDE

Region-Based Kernel Density Estimation (RKDE)

STFPM

Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection

U-Flow

U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold

WinCLIP

WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation