Image Classification on Tiny-ImageNet (Best Acc., Comm., Comp.)
89.9Best AccuracyDreamNet-4
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DreamNet-4Type=DreamNet, Input Size=224^2, #Params=212.03, FLOPs=118.42024.09 | 89.9 | — | — | |
| DreamNet-3MAE-lType=DreamNet, Input Size=224^2, #Params=209.90, FLOPs=149.42024.09 | 89.6 | — | — | |
| DreamNet-3Type=DreamNet, Input Size=224^2, #Params=209.12, FLOPs=83.52024.09 | 89.1 | — | — | |
| DreamNet-3MAE-bType=DreamNet, Input Size=224^2, #Params=209.12, FLOPs=83.52024.09 | 89.1 | — | — | |
| SleepNet-3ViT-lType=SleepNet, Input Size=224^2, #Params=13.40, FLOPs=371.52024.09 | 88.4 | — | — | |
| SleepNet-4Type=SleepNet, Input Size=224^2, #Params=10.14, FLOPs=80.72024.09 | 88.2 | — | — | |
| CvT-W24Type=Conv + Trans, Input Size=384^2, #Params=277.33, FLOPs=193.22024.09 | 88.1 | — | — | |
| SleepNet-3Type=SleepNet, Input Size=224^2, #Params=10.07, FLOPs=60.62024.09 | 88.1 | — | — | |
| SleepNet-3ViT-bType=SleepNet, Input Size=224^2, #Params=10.07, FLOPs=107.32024.09 | 88.1 | — | — | |
| ViTlargeType=Transformer, Input Size=384^2, #Params=307.12, FLOPs=190.72024.09 | 88 | — | — | |
| CoAtNet-3Type=Conv + Trans, Input Size=224^2, #Params=168.12, FLOPs=34.72024.09 | 87.6 | — | — | |
| MAElargeType=Transformer, Input Size=224^2, #Params=304.18, FLOPs=61.92024.09 | 87.1 | — | — | |
| CoAtNet-2Type=Conv + Trans, Input Size=224^2, #Params=75.14, FLOPs=15.72024.09 | 87.1 | — | — | |
| MAEbaseType=Transformer, Input Size=224^2, #Params=86.43, FLOPs=17.62024.09 | 87 | — | — | |
| SleepNet-3MAE-lType=SleepNet, Input Size=224^2, #Params=10.09, FLOPs=126.52024.09 | 86.3 | — | — | |
| ViTbaseType=Transformer, Input Size=224^2, #Params=86.45, FLOPs=55.42024.09 | 86.1 | — | — | |
| SleepNet-3MAE-bType=SleepNet, Input Size=224^2, #Params=10.07, FLOPs=60.62024.09 | 86.1 | — | — | |
| CvT-21Type=Conv + Trans, Input Size=384^2, #Params=32.41, FLOPs=24.92024.09 | 83.1 | — | — | |
| EfficientNet-B7Type=Conv only, Input Size=600^2, #Params=66.44, FLOPs=37.02024.09 | 80.1 | — | — | |
| EfficientNetV2-LType=Conv only, Input Size=480^2, #Params=121.32, FLOPs=53.02024.09 | 77.3 | — | — | |
| DreamNet-2Type=DreamNet, Input Size=224^2, #Params=208.31, FLOPs=52.32024.09 | 71.9 | — | — | |
| ResNet18Type=Conv only, Input Size=224^2, #Params=11.23, FLOPs=1.82024.09 | 68.9 | — | — | |
| ResNet50Type=Conv only, Input Size=224^2, #Params=25.12, FLOPs=3.82024.09 | 68 | — | — | |
| SleepNet-2Type=SleepNet, Input Size=224^2, #Params=10.01, FLOPs=40.52024.09 | 64.2 | — | — | |
| FedAvg-FedPartC=3, Backbone=ResNet-182024.10 | 17.1 | 37 | 98.3 | |
| FedAvg-FedPartC=2, Backbone=ResNet-182024.10 | 15.1 | 24.7 | 65.5 | |
| FedAvg-FNUC=1, Backbone=ResNet-182024.10 | 13.7 | 82.8 | 44.7 | |
| FedAvg-FNUC=2, Backbone=ResNet-182024.10 | 13.7 | 166 | 89.4 | |
| FedAvg-FNUC=3, Backbone=ResNet-182024.10 | 13.7 | 248 | 134 | |
| FedAvg-FedPartC=1, Backbone=ResNet-182024.10 | 12 | 12.3 | 32.8 |