SOTAVerified

Multi-class Anomaly Detection

Multi-class Anomaly Detection is a task that identifies anomalies by jointly learning and detecting outliers across multiple classes, in contrast to traditional Anomaly Detection, which typically focuses on identifying anomalies within a single class.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 39 papers

TitleStatusHype
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly DetectionCode3
Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly DetectionCode3
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly DetectionCode3
A Unified Model for Multi-class Anomaly DetectionCode2
UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly DetectionCode2
DiAD: A Diffusion-based Framework for Multi-class Anomaly DetectionCode2
VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector QuantizationCode1
Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly DetectionCode1
Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly DetectionCode1
Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly DetectionCode1
Learning Unified Reference Representation for Unsupervised Multi-class Anomaly DetectionCode1
Omni-AD: Learning to Reconstruct Global and Local Features for Multi-class Anomaly DetectionCode1
UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly DetectionCode1
Exploring Plain ViT Reconstruction for Multi-class Unsupervised Anomaly DetectionCode0
A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical TransientsCode0
A Classifier-Based Approach to Multi-Class Anomaly Detection Applied to Astronomical Time-SeriesCode0
Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD BenchmarkCode0
Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly DetectionCode0
Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly DetectionCode0
A Comprehensive Library for Benchmarking Multi-class Visual Anomaly DetectionCode0
Pyramid-based Mamba Multi-class Unsupervised Anomaly DetectionCode0
Multi-Class Anomaly Detection based on Regularized Discriminative Coupled hypersphere-based Feature Adaptation—0
Anomaly Detection for Scenario-based Insider Activities using CGAN Augmented Data—0
Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignment—0
OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization—0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.