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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 4856 papers

TitleStatusHype
Divide and Conquer: High-Resolution Industrial Anomaly Detection via Memory Efficient Tiled EnsembleCode9
SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect DetectionCode9
TimesNet: Temporal 2D-Variation Modeling for General Time Series AnalysisCode6
Long-term Forecasting with TiDE: Time-series Dense EncoderCode5
TimeMixer++: A General Time Series Pattern Machine for Universal Predictive AnalysisCode5
VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic FaithfulnessCode5
Reservoir-enhanced Segment Anything Model for Subsurface DiagnosisCode5
aeon: a Python toolkit for learning from time seriesCode5
MOSPAT: AutoML based Model Selection and Parameter Tuning for Time Series Anomaly DetectionCode5
Video-XL: Extra-Long Vision Language Model for Hour-Scale Video UnderstandingCode4
UniTS: A Unified Multi-Task Time Series ModelCode4
Deep Industrial Image Anomaly Detection: A SurveyCode4
Timer: Generative Pre-trained Transformers Are Large Time Series ModelsCode4
Are Transformers Effective for Time Series Forecasting?Code4
A Survey on Diffusion Models for Time Series and Spatio-Temporal DataCode4
Transformers in Time Series: A SurveyCode4
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly DetectionCode3
Deep Learning for Trajectory Data Management and Mining: A Survey and BeyondCode3
Deep Graph Anomaly Detection: A Survey and New PerspectivesCode3
Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample PromptsCode3
TSLANet: Rethinking Transformers for Time Series Representation LearningCode3
RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly DetectionCode3
AER: Auto-Encoder with Regression for Time Series Anomaly DetectionCode3
TOTEM: TOkenized Time Series EMbeddings for General Time Series AnalysisCode3
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly DetectionCode3
AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPCode3
Developing Generalist Foundation Models from a Multimodal Dataset for 3D Computed TomographyCode3
MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled ImagesCode3
Sintel: A Machine Learning Framework to Extract Insights from SignalsCode3
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionCode3
Large-Scale Intelligent MicroservicesCode3
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic ModelCode3
Greykite: Deploying Flexible Forecasting at Scale at LinkedInCode3
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language ModelsCode3
AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly DetectionCode3
ADBench: Anomaly Detection BenchmarkCode3
Hawk: Learning to Understand Open-World Video AnomaliesCode3
Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical ImagesCode3
GluonTS: Probabilistic Time Series Models in PythonCode3
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly DetectionCode3
Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time SeriesCode3
INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual LearningCode3
MMAD: The First-Ever Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly DetectionCode3
A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and LocalizationCode3
The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection BenchmarkCode3
Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly DetectionCode3
3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised AnomalyCode2
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly DetectionCode2
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic ThresholdingCode2
AnoDDPM: Anomaly Detection With Denoising Diffusion Probabilistic Models Using Simplex NoiseCode2
Show:102550
← PrevPage 1 of 98Next →
All datasetsMVTec ADVisAMVTec LOCO ADOne-class CIFAR-10CUHK AvenueShanghaiTechFishyscapes L&FUCR Anomaly ArchiveMPDDBTADOne-class CIFAR-100UBnormal

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CPR-faster(TensorRT)FPS1,016—Unverified
2CPR-fast(TensorRT)FPS362—Unverified
3CPR(TensorRT)FPS130—Unverified
4GLASSDetection AUROC99.9—Unverified
5UniNetDetection AUROC99.9—Unverified
6INP-Fomer ViT-L (model-unified multi-class)Detection AUROC99.8—Unverified
7DDADDetection AUROC99.8—Unverified
8EfficientAD (early stopping)Detection AUROC99.8—Unverified
9PBASDetection AUROC99.8—Unverified
10HETMMDetection AUROC99.8—Unverified
#ModelMetricClaimedVerifiedStatus
1UniNetDetection AUROC99.8—Unverified
2GLADDetection AUROC99.5—Unverified
3UniNet(model-unified multi-class)Detection AUROC99.15—Unverified
4DDADDetection AUROC98.9—Unverified
5Dinomaly ViT-L (model-unified multi-class)Detection AUROC98.9—Unverified
6INP-Former ViT-B (model-unified multi-class)Detection AUROC98.9—Unverified
7DiffusionADDetection AUROC98.8—Unverified
8GLASSDetection AUROC98.8—Unverified
9TransFusionDetection AUROC98.7—Unverified
10HETMMDetection AUROC98.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CSADAvg. Detection AUROC95.3—Unverified
2PSADAvg. Detection AUROC94.9—Unverified