List your company
ResearchFormerly WizWand

Image Classification on ImageNet Real 1.0 (val)

90.2Real Top-1 AccCaiT-M36↑448
81.8884.0486.288.36Apr 22, 2021Jun 18, 2021Aug 15, 2021Oct 12, 2021Dec 8, 2021Feb 4, 2022Apr 3, 2022
Updated 8mo ago

Evaluation results

MethodLinks
CaiT-M36↑448Params=271M, FLOPs=247.8B, Train size=224, Test size=4482021.0490.2
LV-ViT-L↑512Params=151M, FLOPs=214.8B, Train size=448, Test size=5122021.0490.1
Fix-EfficientNet-B8Params=87M, FLOPs=89.5B, Train size=672, Test size=8002021.0490
LV-ViT-L↑448Params=150M, FLOPs=157.2B, Train size=448, Test size=4482021.0489.9
CaiT-S36↑384Params=68M, FLOPs=48.0B, Train size=224, Test size=3842021.0489.8
LV-ViT-L↑448Params=150M, FLOPs=157.2B, Train size=288, Test size=4482021.0489.7
LV-ViT-M↑384Params=56M, FLOPs=42.2B, Train size=224, Test size=3842021.0489.5
NFNet-F3Params=255M, FLOPs=114.8B, Train size=320, Test size=4162021.0489.4
NFNet-F4Params=316M, FLOPs=215.3B, Train size=384, Test size=5122021.0489.4
CaiT-M36Params=271M, FLOPs=53.7B, Train size=224, Test size=2242021.0489.3
LV-ViT-LParams=150M, FLOPs=59.0B, Train size=288, Test size=2882021.0489.3
NFNet-F5Params=377M, FLOPs=289.8B, Train size=416, Test size=5442021.0489.2
LV-ViT-S↑384Params=26M, FLOPs=22.2B, Train size=224, Test size=3842021.0488.9
HAT (+KD)Backbone=ViT-B, Training Set=ImageNet-1K, Knowledge Distillation=true2022.0488.8
LV-ViT-MParams=56M, FLOPs=16.0B, Train size=224, Test size=2242021.0488.4
EfficientNet-B5Params=30M, FLOPs=9.9B, Train size=456, Test size=4562021.0488.3
DeiT (+KD)Backbone=ViT-B, Training Set=ImageNet-1K, Knowledge Distillation=true2022.0488.3
CvT*-LS-21#Param (M)=32.1, Image Size=448x448, FLOPs (G)=34.22021.0788.2
LV-ViT-SParams=26M, FLOPs=6.6B, Train size=224, Test size=2242021.0488.1
CvT*-LS-21#Param (M)=32.1, Image Size=384x384, FLOPs (G)=23.92021.0788
CvT-13#Param (M)=20, Image Size=384x384, FLOPs (G)=31.92021.0787.9
HATBackbone=ViT-B, Training Set=ImageNet-1K2022.0487.9
DeiT-B↑384Params=86M, FLOPs=55.4B, Train size=224, Test size=3842021.0487.7
CvT-21#Param (M)=32, Image Size=384x384, FLOPs (G)=452021.0787.7
CvT*-LS-21#Param (M)=32.1, Image Size=224x224, FLOPs (G)=7.9, Latency (s)=0.1222021.0787.5
CvT*-LS-21S#Param (M)=30.1, Image Size=224x224, FLOPs (G)=11.32021.0787.4
CvT-21#Param (M)=32, Image Size=224x224, FLOPs (G)=10.1, Latency (s)=0.1652021.0787.2
CvT*-LS-17#Param (M)=23.7, Image Size=224x224, FLOPs (G)=9.82021.0787.2
CvT*-LS-13#Param (M)=20.3, Image Size=224x224, FLOPs (G)=4.9, Latency (s)=0.0832021.0787
PyramidATBackbone=ViT-B, Training Set=ImageNet-1K2022.0486.8
DeiT-BParams=86M, FLOPs=17.5B, Train size=224, Test size=2242021.0486.7
DeiT-B#Param (M)=86, Image Size=224x224, FLOPs (G)=17.62021.0786.7
CvT-13#Param (M)=20, Image Size=224x224, FLOPs (G)=6.7, Latency (s)=0.1222021.0786.7
DeiTBackbone=ViT-B, Training Set=ImageNet-1K2022.0486.7
DeiT-SParams=22M, FLOPs=4.6B, Train size=224, Test size=2242021.0485.7
DeiT-S#Param (M)=22, Image Size=224x224, FLOPs (G)=4.62021.0785.7
SAMBackbone=ViT-B, Training Set=ImageNet-1K2022.0485.2
ResNet-152#Param (M)=60, Image Size=224x224, FLOPs (G)=112021.0784.1
ResNet-101#Param (M)=45, Image Size=224x224, FLOPs (G)=7.92021.0783.7
ViT-B/16Params=86M, FLOPs=55.4B, Train size=224, Test size=3842021.0483.6
ResNet-50#Param (M)=25, Image Size=224x224, FLOPs (G)=4.12021.0782.5
VanillaBackbone=ViT-B, Training Set=ImageNet-1K2022.0482.3
ViT-L/16Params=307M, FLOPs=190.7B, Train size=224, Test size=3842021.0482.2