List your company
ResearchFormerly WizWand

Scene Classification on NWPU (10/90 split)

94.56AccuracyViT-B
84.191286.883189.57592.2669Aug 8, 2022
Updated 8mo ago

Evaluation results

MethodLinks
ViT-BPretrain=MAE, Backbone=ViT-B, Method=—2022.0894.56
ViTAE-BPretrain=MAE, Backbone=ViTAE-B, Method=—2022.0894.43
VITAEv2-SPretrain=RSP, Backbone=VITAEv2-S, Method=—2022.0894.41
RingMoPretrain=RingMo [32], Backbone=Swin-B, Method=—2022.0894.25
ViTAE-B + VSAPretrain=MAE, Backbone=ViTAE-B + VSA, Method=—2022.0893.98
ViTAE-B + RVSAPretrain=MAE, Backbone=ViTAE-B + RVSA, Method=—2022.0893.93
ViTAE-B + RVSA♦Pretrain=MAE, Backbone=ViTAE-B + RVSA*, Method=—2022.0893.92
VITAEv2-SPretrain=IMP, Backbone=VITAEv2-S, Method=—2022.0893.9
ViT-B + RVSAPretrain=MAE, Backbone=ViT-B + RVSA, Method=—2022.0893.79
ViT-B + VSAPretrain=MAE, Backbone=ViT-B + VSA, Method=—2022.0893.74
ViT-B + RVSA♦Pretrain=MAE, Backbone=ViT-B + RVSA*, Method=—2022.0893.74
RingMoPretrain=RingMo [32], Backbone=ViT-B, Method=—2022.0893.46
GRMANetPretrain=IMP, Backbone=ResNet-50, Method=GRMANet [73]2022.0893.19
MGML-FENetPretrain=IMP, Backbone=DenseNet-121, Method=MGML-FENet [77]2022.0892.91
F2BRBMPretrain=IMP, Backbone=ResNet-50, Method=F2BRBM [5]2022.0892.74
Swin-TPretrain=IMP, Backbone=Swin-T, Method=—2022.0892.73
LSENetPretrain=IMP, Backbone=VGG-16, Method=LSENet [42]2022.0892.23
EAMPretrain=IMP, Backbone=ResNet-101, Method=EAM [74]2022.0891.91
ViT-BPretrain=IMP, Backbone=ViT-B, Method=—2022.0890.96
MSANetPretrain=IMP, Backbone=ResNet-101, Method=MSANet [75]2022.0890.38
RBFFPretrain=IMP, Backbone=MobileNet-V2 [78], Method=RBFF [79]2022.0884.59