AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Fast and Practical Neural Architecture Search

Jiequan Cui, Pengguang Chen, Ruiyu Li, Shu Liu, Xiaoyong Shen, Jiaya Jia

ICCV 2019 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 69 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
increase E (candidates trained independently) from 5 to 10 (ablation)FPNAS · CIFAR-10 search hyperparameterstop-1 accuracy (%): 95.38 -> 96.01Improved
increase E from 10 to 20 (ablation)FPNAS · CIFAR-10 search hyperparameterstop-1 accuracy (%): 96.01 -> 96.01No clear effect
increase Q (independent training epochs) from 2 to 4 (ablation)FPNAS · CIFAR-10 search hyperparameterstop-1 accuracy (%): 95.80 -> 96.01Improved
increase Q from 4 to 8 (ablation)FPNAS · CIFAR-10 search hyperparameterstop-1 accuracy (%): 96.01 -> 95.93No clear effect
increase P (shared-weight epochs) from 2 to 4 (ablation)FPNAS · CIFAR-10 search hyperparameterstop-1 accuracy (%): 95.59 -> 96.01Improved
increase P from 4 to 8 (ablation)FPNAS · CIFAR-10 search hyperparameterstop-1 accuracy (%): 96.01 -> 95.48Hurt
use different block topologies at different positions instead of one repeated block (ablation)simple 5-block CIFAR-10 networks · CIFAR-10 (27 small networks)accuracy (%)Improved
use fast alternating block search instead of reinforcement learning (ablation)FPNAS search · CIFAR-10 (40 epochs training)top-1 and top-5 accuracyNo clear effect
search networks directly with FPNAS instead of using handcrafted MobileNet V2 (1x)FPNASNet · ImageNet valtop-1 accuracy (%): 72.00 -> 73.34Improved
use FPNASNet encoder instead of MobileNet V2 in PSPNetFPNASNet · ADE20K val (single-scale testing)mean IoU (%): 35.75 -> 36.76Improved
add multiscale testing (ablation)FPNASNet · ADE20K valmean IoU (%): 36.76 -> 37.40Improved
search with FPNAS instead of MnasNet for ~300M FLOPs modelsFPNASNet · ImageNet valtop-1 accuracy (%): 74.00 -> 73.34Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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