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 101–150 of 4856 papers

TitleStatusHype
Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMCode2
Graph Neural Networks in Supply Chain Analytics and Optimization: Concepts, Perspectives, Dataset and BenchmarksCode2
ResAD: A Simple Framework for Class Generalizable Anomaly DetectionCode2
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any GranularityCode2
APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot ADCode2
Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency PerspectiveCode2
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and ProspectsCode2
Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting MaskCode2
Generative AI for Medical Imaging: extending the MONAI FrameworkCode2
SimpleNet: A Simple Network for Image Anomaly Detection and LocalizationCode2
GenDet: Towards Good Generalizations for AI-Generated Image DetectionCode2
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and SegmentationCode2
TAB: Unified Benchmarking of Time Series Anomaly Detection MethodsCode2
TadGAN: Time Series Anomaly Detection Using Generative Adversarial NetworksCode2
Generative Semi-supervised Graph Anomaly DetectionCode2
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality LocalizationCode2
FITS: Modeling Time Series with 10k ParametersCode2
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language ModelsCode2
GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly DetectionCode2
European Space Agency Benchmark for Anomaly Detection in Satellite TelemetryCode2
Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection FrameworkCode2
AD-AGENT: A Multi-agent Framework for End-to-end Anomaly DetectionCode2
3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised AnomalyCode2
Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing ProcessCode2
A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online AdaptationCode2
AdaptCLIP: Adapting CLIP for Universal Visual Anomaly DetectionCode2
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
DiAD: A Diffusion-based Framework for Multi-class Anomaly DetectionCode2
AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial ScenariosCode2
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic ThresholdingCode2
Few-Shot Anomaly-Driven Generation for Anomaly Classification and SegmentationCode2
CSAD: Unsupervised Component Segmentation for Logical Anomaly DetectionCode2
AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2Code2
DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly DetectionCode2
Anomaly Detection via Reverse Distillation from One-Class EmbeddingCode2
Anomaly Transformer: Time Series Anomaly Detection with Association DiscrepancyCode2
Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly DetectionCode2
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly DetectionCode2
Anomaly Detection with Conditioned Denoising Diffusion ModelsCode2
dtaianomaly: A Python library for time series anomaly detectionCode2
Dual Conditioned Motion Diffusion for Pose-Based Video Anomaly DetectionCode2
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level LatenciesCode2
CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency PatchingCode2
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost FilteringCode2
Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language ModelsCode2
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable LocalizationCode2
A Generalizable Anomaly Detection Method in Dynamic GraphsCode2
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLMCode2
GeneralAD: Anomaly Detection Across Domains by Attending to Distorted FeaturesCode2
IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning PerspectiveCode2
Show:102550
← PrevPage 3 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
4UniNetDetection AUROC99.9—Unverified
5GLASSDetection AUROC99.9—Unverified
6PBASDetection AUROC99.8—Unverified
7HETMMDetection AUROC99.8—Unverified
8INP-Fomer ViT-L (model-unified multi-class)Detection AUROC99.8—Unverified
9DDADDetection AUROC99.8—Unverified
10EfficientAD (early stopping)Detection AUROC99.8—Unverified
#ModelMetricClaimedVerifiedStatus
1UniNetDetection AUROC99.8—Unverified
2GLADDetection AUROC99.5—Unverified
3UniNet(model-unified multi-class)Detection AUROC99.15—Unverified
4Dinomaly ViT-L (model-unified multi-class)Detection AUROC98.9—Unverified
5INP-Former ViT-B (model-unified multi-class)Detection AUROC98.9—Unverified
6DDADDetection AUROC98.9—Unverified
7GLASSDetection AUROC98.8—Unverified
8DiffusionADDetection AUROC98.8—Unverified
9TransFusionDetection AUROC98.7—Unverified
10HETMMDetection AUROC98.1—Unverified
#ModelMetricClaimedVerifiedStatus
1CSADAvg. Detection AUROC95.3—Unverified
2PSADAvg. Detection AUROC94.9—Unverified