DeiT III: Revenge of the ViT

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetViT-B @384 (DeiT III, 21k)#125Top 1 Accuracy: 86.7%
image-classification-on-imagenetViT-L#189Top 1 Accuracy: 85.8%Number of params: 304.8MGFLOPs: 191.2
image-classification-on-imagenetViT-B @224 (DeiT III, 21k)#203Top 1 Accuracy: 85.7%
image-classification-on-imagenetViT-H @224 (DeiT III)#243Top 1 Accuracy: 85.2%
image-classification-on-imagenetViT-B @384 (DeiT III)#258Top 1 Accuracy: 85.0%Number of params: 87M
image-classification-on-imagenetViT-L @224 (DeiT III)#269Top 1 Accuracy: 84.9%
image-classification-on-imagenetViT-B @224 (DeiT III)#378Top 1 Accuracy: 83.8%
image-classification-on-imagenetViT-S @384 (DeiT III)#417Top 1 Accuracy: 83.4%Number of params: 22MGFLOPs: 15.5
image-classification-on-imagenetViT-S @224 (DeiT III, 21k)#453Top 1 Accuracy: 83.1%
image-classification-on-imagenetViT-S @224 (DeiT III)#619Top 1 Accuracy: 81.4%
image-classification-on-imagenet-realViT-L @384 (DeiT III, 21k)#53Top 1 Accuracy: 87.7%Number of params: 304M
image-classification-on-imagenet-realViT-H @224 (DeiT III, 21k)#54Top 1 Accuracy: 87.2%Number of params: 632M
image-classification-on-imagenet-realViT-L @224 (DeiT III, 21k)#55Top 1 Accuracy: 87.0%
semantic-segmentation-on-ade20k-valDeiT-L#28mIoU: 55.6
semantic-segmentation-on-ade20k-valDeiT-B#35mIoU: 54.1

Rank counts only results with a code link.