# Image Models

::::{grid} 2
:margin: 1 1 0 0
:gutter: 1

:::{grid-item-card} {material-regular}`model_training;1.5em` AnomalyVFM
:link: ./anomalyvfm
:link-type: doc

Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` AnomalyDINO
:link: ./anomaly_dino
:link-type: doc

Boosting Patch-based Few-shot Anomaly Detection with DINOv2
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` CFA
:link: ./cfa
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` CFM
:link: ./cfm
:link-type: doc

Multimodal Industrial Anomaly Detection by Crossmodal Feature Mapping
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` C-Flow
:link: ./cflow
:link-type: doc

Real-Time Unsupervised Anomaly Detection via Conditional Normalizing Flows
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` CS-Flow
:link: ./csflow
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` DFKDE
:link: ./dfkde
:link-type: doc

Deep Feature Kernel Density Estimation
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` DFM
:link: ./dfm
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` Dinomaly
:link: ./dinomaly
:link-type: doc

Dinomaly: The Less Is More Philosophy in Unsupervised Anomaly Detection

:::

:::{grid-item-card} {material-regular}`model_training;1.5em` DRAEM
:link: ./draem
:link-type: doc

DRÆM – A discriminatively trained reconstruction embedding for surface anomaly detection
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` DSR
:link: ./dsr
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` Efficient AD
:link: ./efficient_ad
:link-type: doc

EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` INP-Former
:link: ./inp_former
:link-type: doc

Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` FastFlow
:link: ./fastflow
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` FRE
:link: ./fre
:link-type: doc

FRE: A Fast Method For Anomaly Detection And Segmentation
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` GANomaly
:link: ./ganomaly
:link-type: doc

GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` GLASS
:link: ./glass
:link-type: doc

A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` GeneralAD
:link: ./general_ad
:link-type: doc

Anomaly Detection Across Domains by Attending to Distorted Features
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` L2BT
:link: ./l2bt
:link-type: doc

Learning to Be a Transformer to Pinpoint Anomalies
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` PaDiM
:link: ./padim
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` Patchcore
:link: ./patchcore
:link-type: doc

Towards Total Recall in Industrial Anomaly Detection
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` PatchFlow
:link: ./patchflow
:link-type: doc

PatchFlow: Leveraging a Flow-Based Model with Patch Features
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` Reverse Distillation
:link: ./reverse_distillation
:link-type: doc

Anomaly Detection via Reverse Distillation from One-Class Embedding.
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` STFPM
:link: ./stfpm
:link-type: doc

Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` SuperSimpleNet
:link: ./supersimplenet
:link-type: doc

SuperSimpleNet: A Unified Surface Defect Detection Model for all Supervision Regimes
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` U-Flow
:link: ./uflow
:link-type: doc

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

:::{grid-item-card} {material-regular}`model_training;1.5em` UniNet
:link: ./uninet
:link-type: doc

UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` VLM-AD
:link: ./vlm_ad
:link-type: doc

VLM-AD: Vision-Language Model for Anomaly Detection
:::

:::{grid-item-card} {material-regular}`model_training;1.5em` WinCLIP
:link: ./winclip
:link-type: doc

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

```{toctree}
:caption: Data
:hidden:

./anomalyvfm
./anomaly_dino
./cfa
./cfm
./cflow
./csflow
./dfkde
./dfm
./dinomaly
./draem
./dsr
./efficient_ad
./fastflow
./fre
./ganomaly
./glass
./general_ad
./inp_former
./l2bt
./padim
./patchcore
./patchflow
./reverse_distillation
./stfpm
./supersimplenet
./uflow
./uninet
./vlm_ad
./winclip
```