List your company
ResearchFormerly WizWand

Classification on Camelyon17

96.5AccuracyDINOv2
58.0268.017887.99Sep 19, 2022Apr 21, 2023Nov 21, 2023Jun 22, 2024Jan 22, 2025Aug 24, 2025Mar 26, 2026
Updated 7mo ago

Evaluation results

MethodLinks
DINOv2Architecture=ViT-g/14, Pre-training Data=LVD, Resolution=518x518, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0196.5
iBOTArchitecture=ViT-L/16, Pre-training Data=IN-21k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.5
AIM-1BArchitecture=ViT-1B/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.5
MAEArchitecture=ViT-2B/14, Pre-training Data=IG-3B, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.4
AIM-0.6BArchitecture=ViT-H/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.3
AIM-3BArchitecture=ViT-3B/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.3
MAEArchitecture=ViT-H/14, Pre-training Data=IN-1k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.2
AIM-7B†Architecture=ViT-7B/14, Pre-training Data=DFN-2B+, Feature Extraction Layer=20th, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0194.2
DINOArchitecture=ViT-B/8, Pre-training Data=IN-1k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0193.7
AIM-7BArchitecture=ViT-7B/14, Pre-training Data=DFN-2B+, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0193.6
AIMv2architecture=ViT-3B/14, Resolution=448px2024.1193.4
BEiTArchitecture=ViT-L/14, Pre-training Data=IN-21k, Evaluation Protocol=Attentive Probing, Backbone State=Frozen2024.0192.8
HCD + VRex*INIT.=HCD, METHOD=VRex*, Backbone=DenseNet-1212026.0386.62
HCD + GroupDROINIT.=HCD, METHOD=GroupDRO, Backbone=DenseNet-1212026.0386.16
HCD + IRMXINIT.=HCD, METHOD=IRMX, Backbone=DenseNet-1212026.0385.91
HCD + IRMINIT.=HCD, METHOD=IRM, Backbone=DenseNet-1212026.0384.31
LISAGroup labels in train set=Yes2022.0977.1
LISAGroup labels in train set?=Yes2022.0977.1
LISAGroup labels in train set?=Yes2022.0977.1
Bonsai + VRexINIT.=Bonsai, METHOD=VRex, Backbone=DenseNet-1212026.0376.39
ERM + GroupDROINIT.=ERM, METHOD=GroupDRO, Backbone=DenseNet-1212026.0376.09
ERM + IRMINIT.=ERM, METHOD=IRM, Backbone=DenseNet-1212026.0375.68
UMIXGroup labels in train set=No2022.0975.1
UMIXGroup labels in train set?=No2022.0975.1
UMIXGroup labels in train set?=No2022.0975.1
FishGroup labels in train set=Yes2022.0974.7
FishGroup labels in train set?=Yes2022.0974.7
FishGroup labels in train set?=Yes2022.0974.7
Bonsai + IRMINIT.=Bonsai, METHOD=IRM, Backbone=DenseNet-1212026.0373.59
ERM + IRMXINIT.=ERM, METHOD=IRMX, Backbone=DenseNet-1212026.0373.49
Bonsai + GroupDROINIT.=Bonsai, METHOD=GroupDRO, Backbone=DenseNet-1212026.0372.82
ERM + VRexINIT.=ERM, METHOD=VRex, Backbone=DenseNet-1212026.0371.6
V-RExGroup labels in train set=Yes2022.0971.5
V-RExGroup labels in train set?=Yes2022.0971.5
V-REXGroup labels in train set?=Yes2022.0971.5
CVaR-DROSetting=group-oblivious2022.0970.5
ERMSetting=group-oblivious2022.0970.3
DomainMixGroup labels in train set=Yes2022.0969.7
DomainMixGroup labels in train set?=Yes2022.0969.7
DomainMixGroup labels in train set?=Yes2022.0969.7
JTTSetting=group-oblivious2022.0969.1
IB-IRMGroup labels in train set=Yes2022.0968.9
IB-IRMGroup labels in train set?=Yes2022.0968.9
IB-IRMGroup labels in train set?=Yes2022.0968.9
GroupDROGroup labels in train set=Yes2022.0968.4
GroupDROGroup labels in train set?=Yes2022.0968.4
GroupDROGroup labels in train set?=Yes2022.0968.4
Focal LossSetting=group-oblivious2022.0968.1
x2-DROSetting=group-oblivious2022.0968
x2-DOROSetting=group-oblivious2022.0968
CVaR-DOROSetting=group-oblivious2022.0967.3
Bonsai + IRMXINIT.=Bonsai, METHOD=IRMX, Backbone=DenseNet-1212026.0364.77
IRMGroup labels in train set=Yes2022.0964.2
IRMGroup labels in train set?=Yes2022.0964.2
IRMGroup labels in train set?=Yes2022.0964.2
CORALGroup labels in train set=Yes2022.0959.5
CORALGroup labels in train set?=Yes2022.0959.5
CORALGroup labels in train set?=Yes2022.0959.5