MobileViT is a lightweight vision transformer that reports 78.4% top-1 accuracy on ImageNet-1k with ~6M parameters, outperforming MobileNetv3 by 3.2% and DeIT by 6.2% at similar size, plus gains on MS-COCO detection.
We set the output dimension of the first feed-forward layer in a transformer layer as2d instead of 4d, a default value in the standard transformer block of Vaswani et al
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
MobileViT is a lightweight vision transformer that reports 78.4% top-1 accuracy on ImageNet-1k with ~6M parameters, outperforming MobileNetv3 by 3.2% and DeIT by 6.2% at similar size, plus gains on MS-COCO detection.