AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

An Efficient Hybrid Vision Transformer for TinyML Applications

Fanhong Zeng, Huanan Li, Juntao Guan, Rui Fan, Tong Wu, Xilong Wang, Rui Lai

ICCV 2025 · Architectures and efficiency › Attention and transformers · approach: Hybrid and interpretable ViT designs · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace last-stage attention with Squeeze-and-Excitation channel module (ablation)MobileViT-XXS · ImageNet-1Ktop-1 accuracy (%): 70.0 -> 70.8Improved
replace last-stage attention with SE (ablation)SHViT-S2 · ImageNet-1Ktop-1 accuracy (%): 74.9 -> 75.3Improved
replace LeanSHSA with 4-head MHSA (ablation)TinyNeXt-M · ImageNet-1K (100 epochs)top-1 accuracy (%) and throughput: 74.1 -> 74.3; 4889 -> 3950 img/sNo clear effect
replace LeanSHSA with bottlenecked SHSA (ablation)TinyNeXt-M · ImageNet-1K (100 epochs)top-1 accuracy (%): 74.1 -> 73.9Hurt
use spatial attention (MHSA) in the last stage instead of SE (ablation)TinyNeXt-M · ImageNet-1K (100 epochs)top-1 accuracy (%): 74.1 -> 74.1; params 2.3M -> 2.7MNo clear effect
use SHSA in the last stage instead of SE (ablation)TinyNeXt-M · ImageNet-1K (100 epochs)top-1 accuracy (%): 74.1 -> 73.6Hurt
replace BatchNorm with LayerNorm (ablation)TinyNeXt-M · ImageNet-1K (100 epochs)top-1 accuracy (%): 74.1 -> 73.8; throughput 4889 -> 4479Hurt
use TinyNeXt-S instead of MobileViT-XXS at similar parametersTinyNeXt-S · ImageNet-1Ktop-1 accuracy (%): 69.0 -> 72.7Improved
use TinyNeXt-M backbone instead of EMO-2M in SSDLiteTinyNeXt-M · COCO 2017mAP: 25.2 -> 25.0No clear effect
use TinyNeXt-S instead of EMO-1M on Jetson NanoTinyNeXt-S · Jetson Nano latencylatency (ms): 26.2 -> 14.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy