EfficientNetV2: Smaller Models and Faster Training

Open paper
Benchmark Model Rank Results
image-classification-on-cifar-10EfficientNetV2-L#17Percentage correct: 99.1
image-classification-on-cifar-10EfficientNetV2-M#24Percentage correct: 99.0
image-classification-on-cifar-10EfficientNetV2-S#31Percentage correct: 98.7
image-classification-on-cifar-100EfficientNetV2-L#13Percentage correct: 92.3
image-classification-on-cifar-100EfficientNetV2-M#14Percentage correct: 92.2
image-classification-on-cifar-100EfficientNetV2-S#19Percentage correct: 91.5
image-classification-on-flowers-102EfficientNetV2-L#18Accuracy: 98.8
image-classification-on-flowers-102EfficientNetV2-M#21Accuracy: 98.5
image-classification-on-flowers-102EfficientNetV2-S#29Accuracy: 97.9
image-classification-on-imagenetEfficientNetV2-XL (21k)#96Top 1 Accuracy: 87.3%Number of params: 208MGFLOPs: 94
image-classification-on-imagenetEfficientNetV2-L (21k)#119Top 1 Accuracy: 86.8%Number of params: 120MGFLOPs: 53
image-classification-on-imagenetEfficientNetV2-M (21k)#160Top 1 Accuracy: 86.2%Number of params: 54MGFLOPs: 24
image-classification-on-imagenetEfficientNetV2-L#201Top 1 Accuracy: 85.7%GFLOPs: 53
image-classification-on-imagenetEfficientNetV2-M#251Top 1 Accuracy: 85.1%
image-classification-on-imagenetEfficientNetV2-S (21k)#268Top 1 Accuracy: 84.9%Number of params: 22MGFLOPs: 8.8
image-classification-on-imagenetEfficientNetV2-S#364Top 1 Accuracy: 83.9%
image-classification-on-stanford-carsEfficientNetV2-L#2Accuracy: 95.1
image-classification-on-stanford-carsEfficientNetV2-M#3Accuracy: 94.6
image-classification-on-stanford-carsEfficientNetV2-S#6Accuracy: 93.8

Rank counts only results with a code link.