List your company

Image Classification on ImageNet V2 1.0 (test)

79.2Top-1 AccuracyViT-H
62.5666.8871.275.52Jul 5, 2021Apr 6, 2022Jan 7, 2023Oct 9, 2023Jul 11, 2024Apr 12, 2025Jan 13, 2026

Evaluation results

MethodLinks
ViT-Hresolution=224, nb params (x10^6)=632.1, throughput (im/s)=112, FLOPs (x10^9)=167.4, Peak Mem (MB)=69842022.0479.2—
ViT-Lresolution=384, fine-tuned=true, nb params (x10^6)=304.8, throughput (im/s)=67, FLOPs (x10^9)=191.2, Peak Mem (MB)=128662022.0479.1—
ViT-Lresolution=224, nb params (x10^6)=304.4, throughput (im/s)=277, FLOPs (x10^9)=61.6, Peak Mem (MB)=37892022.0478.6—
ViT-Bresolution=384, fine-tuned=true, nb params (x10^6)=86.9, throughput (im/s)=190, FLOPs (x10^9)=55.5, Peak Mem (MB)=89562022.0477.9—
ConvNeXt-Lresolution=384, fine-tuned=true, nb params (x10^6)=197.8, throughput (im/s)=115, FLOPs (x10^9)=101, Peak Mem (MB)=119382022.0477.7—
ConvNeXt-XLresolution=384, fine-tuned=true, nb params (x10^6)=350.2, throughput (im/s)=80, FLOPs (x10^9)=179.0, Peak Mem (MB)=162602022.0477.7—
EfficientNetV2-XLresolution=512, nb params (x10^6)=208.1, FLOPs (x10^9)=94.02022.0477—
ConvNeXt-XLresolution=224, nb params (x10^6)=350.2, throughput (im/s)=241, FLOPs (x10^9)=60.9, Peak Mem (MB)=69512022.0477—
Swin-Lresolution=384, nb params (x10^6)=196.7, throughput (im/s)=100, FLOPs (x10^9)=103.9, Peak Mem (MB)=334562022.0477—
EfficientNetV2-Lresolution=480, fine-tuned=true, nb params (x10^6)=118.5, throughput (im/s)=179, FLOPs (x10^9)=53.0, Peak Mem (MB)=95402022.0476.9—
ConvNeXt-Bresolution=384, fine-tuned=true, nb params (x10^6)=88.6, throughput (im/s)=190, FLOPs (x10^9)=45.1, Peak Mem (MB)=78512022.0476.6—
ConvNeXt-Lresolution=224, nb params (x10^6)=197.8, throughput (im/s)=344, FLOPs (x10^9)=34.4, Peak Mem (MB)=48652022.0476.6—
ViT-Bresolution=224, nb params (x10^6)=86.6, throughput (im/s)=831, FLOPs (x10^9)=17.6, Peak Mem (MB)=20782022.0476.5—
Swin-Bresolution=384, fine-tuned=true, nb params (x10^6)=87.9, throughput (im/s)=160, FLOPs (x10^9)=47.0, Peak Mem (MB)=193852022.0476.3—
Swin-Lresolution=224, nb params (x10^6)=196.5, throughput (im/s)=337, FLOPs (x10^9)=34.5, Peak Mem (MB)=73502022.0476.3—
EfficientNetV2-Mresolution=480, fine-tuned=true, nb params (x10^6)=54.1, throughput (im/s)=312, FLOPs (x10^9)=25.0, Peak Mem (MB)=71272022.0475.9—
ConvNeXt-Bresolution=224, nb params (x10^6)=88.6, throughput (im/s)=563, FLOPs (x10^9)=15.4, Peak Mem (MB)=30292022.0475.6—
Swin-Bresolution=224, nb params (x10^6)=87.8, throughput (im/s)=532, FLOPs (x10^9)=15.4, Peak Mem (MB)=46952022.0474.6—
EfficientNetV2-Sresolution=384, fine-tuned=true, nb params (x10^6)=21.5, throughput (im/s)=874, FLOPs (x10^9)=8.5, Peak Mem (MB)=45152022.0474.5—
ViT-Sresolution=224, nb params (x10^6)=22.0, throughput (im/s)=1891, FLOPs (x10^9)=4.6, Peak Mem (MB)=9872022.0473.8—
CvT*-LS-21#Param (M)=32.1, Image Size=448x448, FLOPs (G)=34.22021.0772.9—
CvT*-LS-21#Param (M)=32.1, Image Size=384x384, FLOPs (G)=23.92021.0772.5—
CvT*-LS-21#Param (M)=32.1, Image Size=224x224, FLOPs (G)=7.9, Latency (s)=0.1222021.0771.9—
CvT-13#Param (M)=20, Image Size=384x384, FLOPs (G)=31.92021.0771.9—
CvT-21#Param (M)=32, Image Size=384x384, FLOPs (G)=452021.0771.9—
CvT*-LS-21S#Param (M)=30.1, Image Size=224x224, FLOPs (G)=11.32021.0771.7—
CvT*-LS-17#Param (M)=23.7, Image Size=224x224, FLOPs (G)=9.82021.0771.6—
CvT-21#Param (M)=32, Image Size=224x224, FLOPs (G)=10.1, Latency (s)=0.1652021.0771.3—
DeiT-B#Param (M)=86, Image Size=224x224, FLOPs (G)=17.62021.0770.9—
CvT*-LS-13#Param (M)=20.3, Image Size=224x224, FLOPs (G)=4.9, Latency (s)=0.0832021.0770.5—
CvT-13#Param (M)=20, Image Size=224x224, FLOPs (G)=6.7, Latency (s)=0.1222021.0770.4—
TPTBackbone=ViT-L/142026.017016.4
C-TPTBackbone=ViT-L/142026.0169.914.6
O-TPTBackbone=ViT-L/142026.016910.6
SoCBackbone=ViT-L/142026.0168.910.4
DeiT-S#Param (M)=22, Image Size=224x224, FLOPs (G)=4.62021.0768.5—
AWTShots=162024.0768.22—
Zero-ShotBackbone=ViT-L/142026.0167.93.9
ResNet-152#Param (M)=60, Image Size=224x224, FLOPs (G)=112021.0767—
TPT + CoOpShots=162024.0766.83—
DiffTPT + CoOpShots=162024.0766.8—
ResNet-101#Param (M)=45, Image Size=224x224, FLOPs (G)=7.92021.0765.7—
PromptAlignShots=162024.0765.29—
PLOT++Shots=162024.0765.07—
TPT + CoCoOpShots=162024.0764.85—
ProGradShots=162024.0764.73—
PromptSRCShots=162024.0764.35—
CoOpShots=162024.0764.2—
KgCoOpShots=162024.0764.1—
CoCoOpShots=162024.0764.07—
MaPLeShots=162024.0764.07—
POMPShots=162024.0763.32—
ResNet-50#Param (M)=25, Image Size=224x224, FLOPs (G)=4.12021.0763.3—
DiffTPT + CoCoOpShots=162024.0763.2—