List your company
ResearchFormerly WizWand

Image Classification on Tiny-ImageNet (Best Acc., Comm., Comp.)

89.9Best AccuracyDreamNet-4
8.88429.91750.9571.983Sep 3, 2024Sep 10, 2024Sep 17, 2024Sep 24, 2024Oct 1, 2024Oct 8, 2024Oct 15, 2024
Updated 6mo ago

Evaluation results

MethodLinks
DreamNet-4Type=DreamNet, Input Size=224^2, #Params=212.03, FLOPs=118.42024.0989.9——
DreamNet-3MAE-lType=DreamNet, Input Size=224^2, #Params=209.90, FLOPs=149.42024.0989.6——
DreamNet-3Type=DreamNet, Input Size=224^2, #Params=209.12, FLOPs=83.52024.0989.1——
DreamNet-3MAE-bType=DreamNet, Input Size=224^2, #Params=209.12, FLOPs=83.52024.0989.1——
SleepNet-3ViT-lType=SleepNet, Input Size=224^2, #Params=13.40, FLOPs=371.52024.0988.4——
SleepNet-4Type=SleepNet, Input Size=224^2, #Params=10.14, FLOPs=80.72024.0988.2——
CvT-W24Type=Conv + Trans, Input Size=384^2, #Params=277.33, FLOPs=193.22024.0988.1——
SleepNet-3Type=SleepNet, Input Size=224^2, #Params=10.07, FLOPs=60.62024.0988.1——
SleepNet-3ViT-bType=SleepNet, Input Size=224^2, #Params=10.07, FLOPs=107.32024.0988.1——
ViTlargeType=Transformer, Input Size=384^2, #Params=307.12, FLOPs=190.72024.0988——
CoAtNet-3Type=Conv + Trans, Input Size=224^2, #Params=168.12, FLOPs=34.72024.0987.6——
MAElargeType=Transformer, Input Size=224^2, #Params=304.18, FLOPs=61.92024.0987.1——
CoAtNet-2Type=Conv + Trans, Input Size=224^2, #Params=75.14, FLOPs=15.72024.0987.1——
MAEbaseType=Transformer, Input Size=224^2, #Params=86.43, FLOPs=17.62024.0987——
SleepNet-3MAE-lType=SleepNet, Input Size=224^2, #Params=10.09, FLOPs=126.52024.0986.3——
ViTbaseType=Transformer, Input Size=224^2, #Params=86.45, FLOPs=55.42024.0986.1——
SleepNet-3MAE-bType=SleepNet, Input Size=224^2, #Params=10.07, FLOPs=60.62024.0986.1——
CvT-21Type=Conv + Trans, Input Size=384^2, #Params=32.41, FLOPs=24.92024.0983.1——
EfficientNet-B7Type=Conv only, Input Size=600^2, #Params=66.44, FLOPs=37.02024.0980.1——
EfficientNetV2-LType=Conv only, Input Size=480^2, #Params=121.32, FLOPs=53.02024.0977.3——
DreamNet-2Type=DreamNet, Input Size=224^2, #Params=208.31, FLOPs=52.32024.0971.9——
ResNet18Type=Conv only, Input Size=224^2, #Params=11.23, FLOPs=1.82024.0968.9——
ResNet50Type=Conv only, Input Size=224^2, #Params=25.12, FLOPs=3.82024.0968——
SleepNet-2Type=SleepNet, Input Size=224^2, #Params=10.01, FLOPs=40.52024.0964.2——
FedAvg-FedPartC=3, Backbone=ResNet-182024.1017.13798.3
FedAvg-FedPartC=2, Backbone=ResNet-182024.1015.124.765.5
FedAvg-FNUC=1, Backbone=ResNet-182024.1013.782.844.7
FedAvg-FNUC=2, Backbone=ResNet-182024.1013.716689.4
FedAvg-FNUC=3, Backbone=ResNet-182024.1013.7248134
FedAvg-FedPartC=1, Backbone=ResNet-182024.101212.332.8