AI Paper Atlas

Research map / Architectures and efficiency / CNN design

MicroNet: Improving Image Recognition With Extremely Low FLOPs

Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Lu Yuan, Zicheng Liu, Lei Zhang, Nuno Vasconcelos

ICCV 2021 · Architectures and efficiency › CNN design · approach: Efficient CNN scaling and dynamic inference · 131 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
add Micro-Factorized depthwise convolution (ablation)MobileNet-like baseline · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 44.9 -> 46.4Improved
add Micro-Factorized pointwise convolution (ablation)MobileNet-like baseline + DW · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 46.4 -> 50.0Improved
add lite combination at low levels (ablation)MicroNet static · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 50.0 -> 51.7Improved
add lite combination at both low and high levels instead of low only (ablation)MicroNet · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 51.7 -> 51.2Hurt
add static Shift-Max (ablation)MicroNet static · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 51.7 -> 54.4Improved
use dynamic instead of static Shift-Max (ablation)MicroNet · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 54.4 -> 58.5Improved
use adaptive group number G=sqrt(C/R) instead of fixed G (ablation)Micro-Factorized pointwise conv · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 50.8 -> 51.7Improved
increase group multiplier lambda from 1.0 to 4.0 (ablation)Micro-Factorized pointwise conv · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 51.7 -> 47.6Hurt
use dynamic Shift-Max instead of dynamic ReLU (ablation)MicroNet-M2 · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 56.0 -> 58.5Improved
use dynamic Shift-Max instead of SE+ReLU (ablation)MicroNet-M2 · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 54.4 -> 58.5Improved
add dynamic Shift-Max in all three layers instead of one (A1) (ablation)MicroNet-M2 · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 55.9 -> 58.5Improved
increase K from 2 to 3 in dynamic Shift-Max (J=2) (ablation)MicroNet-M2 · ImageNet (MicroNet-M2 ablation)top-1 accuracy: 58.5 -> 58.1No clear effect

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