List your company
ResearchFormerly WizWand

Fine-Grained Visual Classification on Stanford Dogs (test)

92Top-1 AccRLRR
66.384873.034979.68586.3351May 22, 2017Nov 3, 2018Apr 17, 2020Sep 30, 2021Mar 14, 2023Aug 26, 2024Feb 8, 2026
Updated 8mo ago

Evaluation results

MethodLinks
RLRRBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.47, AugReg=false2024.0392—
ARCBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.25, AugReg=false2024.0391.9—
BiasBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.28, AugReg=false2024.0391.2—
MP-FGVCBackbone=ViT-B-162023.0991—
LoRABackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.44, AugReg=false2024.0391—
PRISBackbone=CNN2023.0990.7—
VPT-ShallowBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.25, AugReg=false2024.0390.7—
IELTBackbone=ViT-B-16, reproduced_from_source=true2023.0990.6—
TransFGBackbone=ViT-B-16, reproduced_from_source=true2023.0990.5—
MSHQPBackbone=CNN2023.0990.4—
API-NetBackbone=CNN2023.0990.3—
VPT-DeepBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.85, AugReg=false2024.0390.2—
RLRR*Backbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.47, AugReg=true2024.0390—
AdapterBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.41, AugReg=false2024.0389.8—
SSFBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.39, AugReg=true2024.0389.6—
Full fine-tuningBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=85.98, AugReg=false2024.0389.4—
SIM-TransBackbone=ViT-B-16, reproduced_from_source=true2023.0989.2—
MRDMNBackbone=CNN2023.0989.1—
ARC*Backbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.25, AugReg=true2024.0389.1—
CALBackbone=CNN2023.0988.7—
Linear probingBackbone=ViT-B/16, Pre-training=ImageNet-21k, Params. (M)=0.18, AugReg=false2024.0386.2—
SPT-DeepBackbone=ViT-B, Pre-training Method=MoCo-v3, Pre-training Dataset=ImageNet-1K, Tuning Depth=Deep2024.0285.84—
FDLBackbone=CNN2023.0984.9—
SPT-ShallowBackbone=ViT-B, Pre-training Method=MoCo-v3, Pre-training Dataset=ImageNet-1K, Tuning Depth=Shallow2024.0284.17—
PC-DenseNet-161backbone=DenseNet-161, pairwise_confusion=true2017.0583.752.57
GateVPTBackbone=ViT-B, Pre-training Method=MoCo-v3, Pre-training Dataset=ImageNet-1K2024.0283.37—
VPT-DeepBackbone=ViT-B, Pre-training Method=MoCo-v3, Pre-training Dataset=ImageNet-1K, Tuning Depth=Deep2024.0283.33—
PC-BilinearCNNbackbone=VGG-16, pairwise_confusion=true2017.0583.040.91
SPT-DeepBackbone=ViT-B, Pre-training Method=MAE, Pre-training Dataset=ImageNet-1K, Tuning Depth=Deep2024.0282.23—
BilinearCNNbackbone=VGG-162017.0582.13—
VPT-ShallowBackbone=ViT-B, Pre-training Method=MoCo-v3, Pre-training Dataset=ImageNet-1K, Tuning Depth=Shallow2024.0281.97—
FullBackbone=ViT-B, Pre-training Method=MoCo-v3, Pre-training Dataset=ImageNet-1K, Tuning Depth=Full2024.0281.19—
DenseNet-161backbone=DenseNet-1612017.0581.18—
Krause et al.2017.0580.6—
Zhang et al.2017.0580.43—
FullBackbone=ViT-B, Pre-training Method=MAE, Pre-training Dataset=ImageNet-1K, Tuning Depth=Full2024.0280.38—
SPT-ShallowBackbone=ViT-B, Pre-training Method=MAE, Pre-training Dataset=ImageNet-1K, Tuning Depth=Shallow2024.0280.01—
GateVPTBackbone=ViT-B, Pre-training Method=MAE, Pre-training Dataset=ImageNet-1K2024.0278.9—
VPT-DeepBackbone=ViT-B, Pre-training Method=MAE, Pre-training Dataset=ImageNet-1K, Tuning Depth=Deep2024.0278.83—
VPT-ShallowBackbone=ViT-B, Pre-training Method=MAE, Pre-training Dataset=ImageNet-1K, Tuning Depth=Shallow2024.0277.07—
PANDStudent=ResNet-182026.0274.98—
PANDStudent=MobileNet-V22026.0274.52—
PC-ResNet-50backbone=ResNet-50, pairwise_confusion=true2017.0573.353.43
VL2LiteStudent=MobileNet-V22026.0273.28—
VL2LiteStudent=ResNet-182026.0273.14—
KDStudent=MobileNet-V22026.0273.02—
ResNet-50backbone=ResNet-502017.0569.92—
RKDStudent=MobileNet-V22026.0269.45—
RKDStudent=ResNet-182026.0269.03—
KDStudent=ResNet-182026.0268.8—
w/o KDStudent=MobileNet-V22026.0268.28—
w/o KDStudent=ResNet-182026.0267.37—