Command Palette

Search for a command to run...

异常检测

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。

MVTec AD
GLASS
VisA
ReContrast
MVTec LOCO AD
CSAD
One-class CIFAR-10
CSI
CUHK Avenue
HF2VAD+SSPCAB
ShanghaiTech
SSMTL+UBnormal
UCR Anomaly Archive
Auto-Encoder with Regression (AER)
Fishyscapes L&F
cDNP+OE
One-class CIFAR-100
GeneralAD
MPDD
GLASS
UBnormal
TimeSformer
BTAD
MuSc (zero-shot)
UCSD Ped2
Background-Agnostic
Unlabeled CIFAR-10 vs CIFAR-100
CSI
Fashion-MNIST
One-class ImageNet-30
CSI
Road Anomaly
RbA
Numenta Anomaly Benchmark
HTM AL
Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)
AeBAD-S
MSFR
Fishyscapes
RPL+CoroCL
AeBAD-V
MMR
MNIST
Leave-One-Class-Out ImageNet-30
BCE-CLIP (OE)
Leave-One-Class-Out CIFAR-10
Hyper-Kvasir Dataset
InsPLAD
AttentDifferNet (SENet-AlexNet)
LAG
CCD
Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102
Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200
Lost and Found
PHEVA
MPED-RNN
MVTEC AD textures
Surface Defect Saliency of Magnetic Tile
HETMM
Cats-and-Dogs
Self-Supervised One-class SVM, RBF kernel
DIOR
Self-Supervised One-class SVM, RBF kernel
Corridor
Two-stream
UCSD Peds2
UEA time-series datasets
SINBAD
voraus-AD
MVT-Flow
ODDS
kNN
MVTec AD Textures Domain Generalization
FABLE
PAD Dataset
SplatPose
Thyroid
RCALAD
MVTEC 3D-AD
CDO
Vehicle Claims
Random Forest
CIFAR-10
Real 3D-AD
Reg 3D-AD
NB15-Backdoor
WFDD
GLASS
MNIST-test
OGNET
NB15-Analysis
BottleCap
DFC
SMD
MAAT
ASSIRA Cat Vs Dog
Shell-based Anomaly (supervisered)
Street Scene
PGM
IITB Corridor
NB15-DoS
DIF
Census
DevNet
TII-SSRC-23
SVHN
RCALAD
MVTec 3D-AD (RGB)
ADNI
Brainomaly
kdd 99
PCA via oversampling
AG News
DATE
Forest CoverType
KDD Cup 1999
COCO-OOC
Musk v1
ShanghaiTech Campus
TSGAD
MIT-BIH Arrhythmia Database
KSDD2
SAA+
Kaggle-Credit Card Fraud Dataset
STL-10
Shell-based Anomaly (supervised)
UCF-Crime
MVTec-AD