MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
MobileViT-S
#790
Top 1 Accuracy: 78.4%
Number of params: 5.6M
image-classification-on-imagenet
MobileViT-XS
#907
Top 1 Accuracy: 74.8%
Number of params: 2.3M
GFLOPs: 0.7
Rank counts only results with a code link.