MicroViTv2 improves accuracy by up to 0.5% over MicroViT and beats MobileViTv2, EdgeNeXt, and EfficientViT on ImageNet-1K and COCO while delivering faster inference and lower energy on Jetson hardware through reparameterization and SDTA.
Efficientvit: Memory efficient vision transformer with cascaded group attention
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers
MicroViTv2 improves accuracy by up to 0.5% over MicroViT and beats MobileViTv2, EdgeNeXt, and EfficientViT on ImageNet-1K and COCO while delivering faster inference and lower energy on Jetson hardware through reparameterization and SDTA.