SOTAVerified

Anomaly Classification

Anomaly Classification is the task of identifying and categorizing different types of anomalies in visual data, rather than simply detecting whether an input is normal or anomalous. Unlike anomaly detection, which is typically a binary classification (normal vs. anomaly), anomaly classification requires distinguishing between multiple anomaly classes—each representing a distinct type of anomaly or irregularity. This task is critical in real-world applications such as industrial inspection, where different anomalies may require different responses or interventions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 72 papers

TitleStatusHype
MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled ImagesCode3
Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical ImagesCode3
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
DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image GenerationCode2
SoftPatch+: Fully Unsupervised Anomaly Classification and SegmentationCode2
MedIAnomaly: A comparative study of anomaly detection in medical imagesCode2
Anomaly Detection via Reverse Distillation from One-Class EmbeddingCode2
AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial ScenariosCode2
WinCLIP: Zero-/Few-Shot Anomaly Classification and SegmentationCode2
Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language ModelsCode2
SimpleNet: A Simple Network for Image Anomaly Detection and LocalizationCode2
Towards Total Recall in Industrial Anomaly DetectionCode2
Few-Shot Anomaly-Driven Generation for Anomaly Classification and SegmentationCode2
CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing FlowsCode1
CutPaste: Self-Supervised Learning for Anomaly Detection and LocalizationCode1
DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectionCode1
Component-aware anomaly detection framework for adjustable and logical industrial visual inspectionCode1
Sub-Image Anomaly Detection with Deep Pyramid CorrespondencesCode1
Power System Anomaly Detection and Classification Utilizing WLS-EKF State Estimation and Machine LearningCode1
PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and SegmentationCode1
Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and LocalizationCode1
Large Language Models for Forecasting and Anomaly Detection: A Systematic Literature Review—0
TAB: Text-Align Anomaly Backbone Model for Industrial Inspection Tasks—0
Anomaly Classification in Distribution Networks Using a Quotient Gradient System—0
Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images—0
Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection—0
CAMLPAD: Cybersecurity Autonomous Machine Learning Platform for Anomaly Detection—0
Can Multimodal Large Language Models be Guided to Improve Industrial Anomaly Detection?—0
CEReBrO: Compact Encoder for Representations of Brain Oscillations Using Efficient Alternating Attention—0
Circuit design in biology and machine learning. II. Anomaly detection—0
Classification of Anomalies in Telecommunication Network KPI Time Series—0
CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation—0
Comparison of Evolving Granular Classifiers applied to Anomaly Detection for Predictive Maintenance in Computing Centers—0
Conditioning Latent-Space Clusters for Real-World Anomaly Classification—0
Deep Subspace Learning for Surface Anomaly Classification Based on 3D Point Cloud Data—0
Detecting, Localising and Classifying Polyps from Colonoscopy Videos using Deep Learning—0
Dual-Image Enhanced CLIP for Zero-Shot Anomaly Detection—0
Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation—0
Endowing Robots with Longer-term Autonomy by Recovering from External Disturbances in Manipulation through Grounded Anomaly Classification and Recovery Policies—0
Evaluation of Key Spatiotemporal Learners for Print Track Anomaly Classification Using Melt Pool Image Streams—0
Generalizing Few Data to Unseen Domains Flexibly Based on Label Smoothing Integrated with Distributionally Robust Optimization—0
Imitating Radiological Scrolling: A Global-Local Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification—0
Label Assisted Autoencoder for Anomaly Detection in Power Generation Plants—0
Residual Generation Using Physically-Based Grey-Box Recurrent Neural Networks For Engine Fault Diagnosis—0
SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets—0
Spatially-Preserving Flattening for Location-Aware Classification of Findings in Chest X-Rays—0
STC-IDS: Spatial-Temporal Correlation Feature Analyzing based Intrusion Detection System for Intelligent Connected Vehicles—0
SunDown: Model-driven Per-Panel Solar Anomaly Detection for Residential Arrays—0
SuperAD: A Training-free Anomaly Classification and Segmentation Method for CVPR 2025 VAND 3.0 Workshop Challenge Track 1: Adapt & Detect—0
Supervised Contrastive Learning to Classify Paranasal Anomalies in the Maxillary Sinus—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsGoodsADMVTecADMVTec-ACVisA-AC

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PatchCore-100%AUPR86.1—Unverified
2MiniMaxAD-frAUROC86.1—Unverified
3PatchCore-1%AUPR83.3—Unverified
4SimpleNetAUPR78.7—Unverified
5CFLOW-ADAUPR75.3—Unverified
6NSAAUPR71.8—Unverified
7DRAEMAUPR71—Unverified
8SPADEAUPR68.7—Unverified
9RD4ADAUPR68.2—Unverified
10f-AnoGANAUPR66.6—Unverified
#ModelMetricClaimedVerifiedStatus
1VELMAccuracy (% )81.4—Unverified
2EchoAccuracy (% )72.9—Unverified
#ModelMetricClaimedVerifiedStatus
1VELMAccuracy (% )84—Unverified
#ModelMetricClaimedVerifiedStatus
1VELMAccuracy(%)69.6—Unverified