Command Palette
Search for a command to run...
Out-of-Distribution Detection
Out-of-Distribution Detection refers to identifying anomalous samples that do not belong to the distribution of training data in computer vision tasks. This task aims to enhance the robustness and generalization ability of models, effectively avoiding misjudgments on unknown data by detecting and filtering these anomalies, thus improving the safety and reliability of the system. In practical applications, this technology is crucial for boosting system performance in fields such as autonomous driving and medical image analysis.
ImageNet-1k vs Textures
ViM (BiT-S-R101×1)
ImageNet-1k vs iNaturalist
NNGuide (RegNet)
ImageNet-1k vs Places
BATS (ResNet-50)
ImageNet-1k vs SUN
LINe (ResNet50)
ImageNet-1k vs Curated OODs (avg.)
ASH-S (ResNet-50)
CIFAR-10 vs CIFAR-100
Wide 40-2 + OECC
CIFAR-100 vs CIFAR-10
WRN 40-2 + OECC
CIFAR-10
ResNet 34 + OECC+GM
ImageNet-1k vs OpenImage-O
NNGuide (RegNet)
STL-10
Mixup (Gaussian)
ImageNet-1k vs NINCO
Forte
CIFAR-100 vs SVHN
OECC + MD
ADE-OoD
RbA
MS-1M vs. IJB-C
ResNeXt50 + FSSD
CIFAR-100
Wide ResNet 40x2
ImageNet dogs vs ImageNet non-dogs
ResNet34 + FSSD
ImageNet-1K vs ImageNet-O
NNGuide-ViM (ViT-B/16)
CIFAR-10 vs SVHN
CIFAR-10 vs LSUN (R)
SVHN vs Uniform
Fashion-MNIST
PAE
CIFAR-100 vs ImageNet (R)
DenseNet-BC-100
20 Newsgroups
2-Layered GRU
SVHN vs Gaussian
SVHN vs ImageNet (C)
CIFAR-10 vs ImageNet (C)
Near-OOD
CIFAR-100 vs iSUN
DenseNet-BC-100
CIFAR-10 vs Uniform
CIFAR-10 vs LSUN (C)
CIFAR-10 vs Gaussian
CIFAR-100 vs ImageNet (C)
CIFAR-100 vs Gaussian
SVHN vs LSUN (C)
SVHN vs CIFAR-100
SVHN vs ImageNet (R)
CIFAR-100 vs LSUN (R)
DenseNet-BC-100
CIFAR-10 vs ImageNet (R)
SVHN vs LSUN (R)
Far-OOD
ISH (ResNet50)
CIFAR-100 vs LSUN (C)
SVHN vs iSUN
CIFAR-10 vs iSUN
CIFAR-100 vs Uniform
SVHN vs CIFAR-10
cifar100
Wide Resnet 40x2
CIFAR-10 vs CIFAR-10.1
ERD (ResNet18)
ImageNet-1K vs ImageNet-C
Wide ResNet 40x2
cifar10
SST
ImageNet-1K vs SSB-hard