MicroViT combines group convolutions with single-head, reduced-channel self-attention to build a lightweight vision transformer that reportedly outperforms MobileViT in speed and energy on edge hardware.
Spik- ingvit: a multi-scale spiking vision transformer model for event-based object detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device
MicroViT combines group convolutions with single-head, reduced-channel self-attention to build a lightweight vision transformer that reportedly outperforms MobileViT in speed and energy on edge hardware.