AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

On Network Design Spaces for Visual Recognition

Ilija Radosavovic, Justin Johnson, Saining Xie, Wan-Yen Lo, Piotr Dollar

ICCV 2019 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 133 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
compare design spaces by distributions instead of minimum error (point estimate)ResNet design space, 100 vs 1000 samples · CIFAR-10conclusion reliability: In 90% of cases M has lower minimum than B; KS D=0.079, p=0.60Improved
normalize error distributions by model complexity (params or flops)ResNeXt-A vs ResNeXt-B comparison · CIFAR-10error EDF gapImproved
add residual connections (ResNet vs Vanilla design space) (ablation)Vanilla design space · CIFAR-10fraction of models with error under 8%: ~15% -> >80%Improved
use ResNet instead of Vanilla design space for random search (ablation)random search · CIFAR-10random search efficiencyImproved
increase number of sampled models for EDF estimation (10 to 100 to 1000) (ablation)ResNet design space EDF · CIFAR-10KS statistic D vs full 25k sample: D about 0.1 at 100 samples; saturates at 1000Improved
use newer NAS design spaces (DARTS) instead of NASNet and AmoebaNAS design spaces · CIFAR-10error EDF: max KS D=0.51 between DARTS and NASNetImproved
use ResNeXt-B design space instead of DARTS (params normalized)standard vs NAS design space · CIFAR-10 (normalized for params)error EDF: KS D=0.09No clear effect
use DARTS instead of ResNeXt-B (flops normalized)standard vs NAS design space · CIFAR-10 (normalized for flops)error EDFImproved
use enhanced training setup (600 epochs, deep supervision, Cutout, DropPath)ResNet-110 · CIFAR-10test error (%): 5.91 -> 3.65Improved
use enhanced training setupResNeXt* · CIFAR-10test error (%): 4.90 -> 2.75Improved
use enhanced training setupDARTS* · CIFAR-10test error (%): 5.21 -> 2.63Improved
average error over 1 to 3 training runs (ablation)error EDFs of 5k models · CIFAR-10KS statistic D: D<0.009No 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