Anomaly Detection
异常检测是一种二分类任务,旨在识别数据集中显著偏离大多数数据的不寻常或意外模式。该任务的目标是发现这些异常点,它们可能代表错误、欺诈或其他类型的异常事件,并对其进行标记以便进一步调查。异常检测在金融风控、网络安全、医疗诊断等领域具有重要应用价值。
ADNI
Brainomaly
AeBAD-S
MSFR
AeBAD-V
MMR
AG News
DATE
Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102
Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)
Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200
ASSIRA Cat Vs Dog
Shell-based Anomaly (supervisered)
BottleCap
DFC
BTAD
MuSc (zero-shot)
Cats-and-Dogs
Self-Supervised One-class SVM, RBF kernel
Census
DevNet
CUHK Avenue
MULDE-object-centric-micro
CIFAR-10
COCO-OOC
Corridor
Two-stream
DIOR
Self-Supervised One-class SVM, RBF kernel
Fashion-MNIST
Fishyscapes
RPL+CoroCL
Fishyscapes L&F
cDNP+OE
Forest CoverType
Hyper-Kvasir Dataset
IITB Corridor
InsPLAD
AttentDifferNet (SENet-AlexNet)
Kaggle-Credit Card Fraud Dataset
kdd 99
PCA via oversampling
KDD Cup 1999
KSDD2
SAA+
LAG
CCD
Leave-One-Class-Out CIFAR-10
Leave-One-Class-Out ImageNet-30
BCE-CLIP (OE)
Lost and Found
MIT-BIH Arrhythmia Database
MNIST
MNIST-test
OGNET
MPDD
GLASS
Musk v1
MVTEC 3D-AD
CDO
MVTec 3D-AD (RGB)
MVTec AD
GLASS
MVTec-AD
MVTEC AD textures
MVTec AD Textures Domain Generalization
FABLE
MVTec LOCO AD
CSAD
NB15-Analysis
NB15-Backdoor
NB15-DoS
DIF
Numenta Anomaly Benchmark
HTM AL
ODDS
kNN
One-class CIFAR-10
CLIP (OE)
One-class CIFAR-100
GeneralAD
One-class ImageNet-30
CSI
PHEVA
MPED-RNN
PAD Dataset
SplatPose
Real 3D-AD
Reg 3D-AD
Road Anomaly
RbA
ShanghaiTech
DAC(STG-NF + Jigsaw)
ShanghaiTech Campus
TSGAD
SMD
MAAT
STL-10
Shell-based Anomaly (supervised)
Street Scene
PGM
Surface Defect Saliency of Magnetic Tile
HETMM
SVHN
RCALAD
Thyroid
RCALAD
TII-SSRC-23
UBnormal
STG-NF - Supervised
UCF-Crime
UCR Anomaly Archive
Auto-Encoder with Regression (AER)
UCSD Ped2
DMAD
UCSD Peds2
UEA time-series datasets
SINBAD
Unlabeled CIFAR-10 vs CIFAR-100
CSI
Vehicle Claims
Random Forest
VisA
GLAD
voraus-AD
MVT-Flow
WFDD
GLASS