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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 3231–3240 of 4856 papers

Title	Date	Tasks	Status
TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detection	Jan 21, 2025	Anomaly DetectionMisinformation	—Unverified
TADPOLE: Task ADapted Pre-Training via AnOmaLy DEtection	Nov 1, 2021	Anomaly DetectionData Augmentation	—Unverified
TAGA: Self-supervised Learning for Template-free Animatable Gaussian Articulated Model	Jan 1, 2025	Anomaly DetectionSelf-Supervised Learning	—Unverified
Tail of Distribution GAN (TailGAN): Generative-Adversarial-Network-Based Boundary Formation	Jul 24, 2021	Anomaly DetectionGenerative Adversarial Network	—Unverified
Tailoring Machine Learning for Process Mining	Jun 17, 2023	Anomaly Detection	—Unverified
Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection	Jul 5, 2025	3D Anomaly DetectionAnomaly Detection	—Unverified
Targeted collapse regularized autoencoder for anomaly detection: black hole at the center	Jun 22, 2023	Anomaly Detection	—Unverified
Task Agnostic and Post-hoc Unseen Distribution Detection	Jul 26, 2022	Anomaly DetectionOut of Distribution (OOD) Detection	—Unverified
Task-agnostic Continual Learning with Hybrid Probabilistic Models	Jun 24, 2021	Anomaly DetectionContinual Learning	—Unverified
Task-aware Similarity Learning for Event-triggered Time Series	Jul 17, 2022	Anomaly DetectionTime Series	—Unverified

Show:10 25 50

← PrevPage 324 of 486Next →

All datasets MVTec AD VisA MVTec LOCO AD One-class CIFAR-10 CUHK Avenue ShanghaiTech Fishyscapes L&F UCR Anomaly Archive MPDD BTAD One-class CIFAR-100 UBnormal

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	CPR-faster(TensorRT)	FPS	1,016	—	Unverified
2	CPR-fast(TensorRT)	FPS	362	—	Unverified
3	CPR(TensorRT)	FPS	130	—	Unverified
4	UniNet	Detection AUROC	99.9	—	Unverified
5	GLASS	Detection AUROC	99.9	—	Unverified
6	PBAS	Detection AUROC	99.8	—	Unverified
7	HETMM	Detection AUROC	99.8	—	Unverified
8	INP-Fomer ViT-L (model-unified multi-class)	Detection AUROC	99.8	—	Unverified
9	DDAD	Detection AUROC	99.8	—	Unverified
10	EfficientAD (early stopping)	Detection AUROC	99.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UniNet	Detection AUROC	99.8	—	Unverified
2	GLAD	Detection AUROC	99.5	—	Unverified
3	UniNet(model-unified multi-class)	Detection AUROC	99.15	—	Unverified
4	Dinomaly ViT-L (model-unified multi-class)	Detection AUROC	98.9	—	Unverified
5	INP-Former ViT-B (model-unified multi-class)	Detection AUROC	98.9	—	Unverified
6	DDAD	Detection AUROC	98.9	—	Unverified
7	GLASS	Detection AUROC	98.8	—	Unverified
8	DiffusionAD	Detection AUROC	98.8	—	Unverified
9	TransFusion	Detection AUROC	98.7	—	Unverified
10	HETMM	Detection AUROC	98.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CSAD	Avg. Detection AUROC	95.3	—	Unverified
2	PSAD	Avg. Detection AUROC	94.9	—	Unverified