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 51–100 of 4856 papers

TitleStatusHype
AdaptCLIP: Adapting CLIP for Universal Visual Anomaly DetectionCode2
Learning to Detect Multi-class Anomalies with Just One Normal Image PromptCode2
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-LearningCode2
Few-Shot Anomaly-Driven Generation for Anomaly Classification and SegmentationCode2
Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly DetectionCode2
ReplayCAD: Generative Diffusion Replay for Continual Anomaly DetectionCode2
Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language ModelsCode2
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost FilteringCode2
ZClip: Adaptive Spike Mitigation for LLM Pre-TrainingCode2
Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly DetectionCode2
Towards Training-free Anomaly Detection with Vision and Language Foundation ModelsCode2
Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing ProcessCode2
Bayesian Prompt Flow Learning for Zero-Shot Anomaly DetectionCode2
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLMCode2
UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly DetectionCode2
One-for-More: Continual Diffusion Model for Anomaly DetectionCode2
Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly DetectionCode2
dtaianomaly: A Python library for time series anomaly detectionCode2
VUS: Effective and Efficient Accuracy Measures for Time-Series Anomaly DetectionCode2
3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised AnomalyCode2
A Survey on Diffusion Models for Anomaly DetectionCode2
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable LocalizationCode2
SoftPatch+: Fully Unsupervised Anomaly Classification and SegmentationCode2
Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly DetectionCode2
A Generalizable Anomaly Detection Method in Dynamic GraphsCode2
Tests for model misspecification in simulation-based inference: from local distortions to global model checksCode2
Multi-Sensor Object Anomaly Detection: Unifying Appearance, Geometry, and Internal PropertiesCode2
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any GranularityCode2
Quantized symbolic time series approximationCode2
Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and BenchmarksCode2
LogLLM: Log-based Anomaly Detection Using Large Language ModelsCode2
A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly DetectionCode2
ResAD: A Simple Framework for Class Generalizable Anomaly DetectionCode2
AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial ScenariosCode2
CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency PatchingCode2
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly DetectionCode2
Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection FrameworkCode2
Self-supervised Anomaly Detection Pretraining Enhances Long-tail ECG DiagnosisCode2
CSAD: Unsupervised Component Segmentation for Logical Anomaly DetectionCode2
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series AnalysisCode2
GeneralAD: Anomaly Detection Across Domains by Attending to Distorted FeaturesCode2
VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentationCode2
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language ModelsCode2
Odd-One-Out: Anomaly Detection by Comparing with NeighborsCode2
European Space Agency Benchmark for Anomaly Detection in Satellite TelemetryCode2
Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A BenchmarkCode2
Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMCode2
GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly DetectionCode2
AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2Code2
Show:102550
← PrevPage 2 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
6HETMMDetection AUROC99.8—Unverified
7INP-Fomer ViT-L (model-unified multi-class)Detection AUROC99.8—Unverified
8EfficientAD (early stopping)Detection AUROC99.8—Unverified
9DDADDetection AUROC99.8—Unverified
10PBASDetection AUROC99.8—Unverified
#ModelMetricClaimedVerifiedStatus
1UniNetDetection AUROC99.8—Unverified
2GLADDetection AUROC99.5—Unverified
3UniNet(model-unified multi-class)Detection AUROC99.15—Unverified
4INP-Former ViT-B (model-unified multi-class)Detection AUROC98.9—Unverified
5DDADDetection AUROC98.9—Unverified
6Dinomaly ViT-L (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