AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

Zhihang Yuan, Bingzhe Wu, Guangyu Sun, Zheng Liang, Shiwan Zhao, Weichen Bi

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search

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
use S2DNAS instead of BranchyNet early exitingResNet-20 · CIFAR-10accuracy: from 91.37% to 91.41%Improved
apply S2DNAS dynamic inference to the static modelResNet-20 · CIFAR-10FLOPs: 41M -> 16M (61%)Improved
apply S2DNAS dynamic inference to the static modelVGG16-BN · CIFAR-10FLOPs: 79% reduction with a slight accuracy dropImproved
add BlockDrop controller for dynamic layer skippingResNet-20 · CIFAR-100FLOPs: 41M -> 53M (-29%)Hurt
raise the exit thresholds (more computation) (ablation)S2DNAS multi-stage models · CIFAR-10 and CIFAR-100accuracyImproved
use MSDNet instead of S2DNAS at low budgetDenseNet-like model · CIFAR-10accuracy vs FLOPs: MSDNet better at FLOPs around 15MMixed

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