SOTAVerified

Anomaly Detection

Anomaly Detection is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.

[Image source]: GAN-based Anomaly Detection in Imbalance Problems

Papers

Showing 126150 of 4856 papers

TitleStatusHype
AdaptCLIP: Adapting CLIP for Universal Visual Anomaly DetectionCode2
Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly DetectionCode2
Few-Shot Anomaly-Driven Generation for Anomaly Classification and SegmentationCode2
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly DetectionCode2
DiAD: A Diffusion-based Framework for Multi-class Anomaly DetectionCode2
dtaianomaly: A Python library for time series anomaly detectionCode2
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable LocalizationCode2
Anomaly Detection with Conditioned Denoising Diffusion ModelsCode2
Anomaly Detection via Reverse Distillation from One-Class EmbeddingCode2
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly DetectionCode2
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic ThresholdingCode2
CSAD: Unsupervised Component Segmentation for Logical Anomaly DetectionCode2
CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency PatchingCode2
AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial ScenariosCode2
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly DetectionCode2
European Space Agency Benchmark for Anomaly Detection in Satellite TelemetryCode2
AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2Code2
Anomaly Transformer: Time Series Anomaly Detection with Association DiscrepancyCode2
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost FilteringCode2
Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language ModelsCode2
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality LocalizationCode2
GeneralAD: Anomaly Detection Across Domains by Attending to Distorted FeaturesCode2
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLMCode2
IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning PerspectiveCode2
Show:102550
← PrevPage 6 of 195Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CPR-faster(TensorRT)FPS1,016Unverified
2CPR-fast(TensorRT)FPS362Unverified
3CPR(TensorRT)FPS130Unverified
4GLASSDetection AUROC99.9Unverified
5UniNetDetection AUROC99.9Unverified
6HETMMDetection AUROC99.8Unverified
7INP-Fomer ViT-L (model-unified multi-class)Detection AUROC99.8Unverified
8EfficientAD (early stopping)Detection AUROC99.8Unverified
9DDADDetection AUROC99.8Unverified
10PBASDetection AUROC99.8Unverified
#ModelMetricClaimedVerifiedStatus
1UniNetDetection AUROC99.8Unverified
2GLADDetection AUROC99.5Unverified
3UniNet(model-unified multi-class)Detection AUROC99.15Unverified
4INP-Former ViT-B (model-unified multi-class)Detection AUROC98.9Unverified
5DDADDetection AUROC98.9Unverified
6Dinomaly ViT-L (model-unified multi-class)Detection AUROC98.9Unverified
7DiffusionADDetection AUROC98.8Unverified
8GLASSDetection AUROC98.8Unverified
9TransFusionDetection AUROC98.7Unverified
10HETMMDetection AUROC98.1Unverified
#ModelMetricClaimedVerifiedStatus
1CSADAvg. Detection AUROC95.3Unverified
2PSADAvg. Detection AUROC94.9Unverified