AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

One-Shot Neural Architecture Search via Self-Evaluated Template Network

Xuanyi Dong, Yi Yang

ICCV 2019 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 205 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
train the template network stochastically (SETN) instead of standard classification training (SETN-NON) (ablation)SETN · CIFAR-10 (with CutOut)test error (%): 3.12 -> 2.69Improved
train the template network stochastically (SETN) instead of standard classification training (SETN-NON) (ablation)SETN · CIFAR-100 (with CutOut)test error (%): 18.27 -> 17.25Improved
use independent per-cell sampling (SETN) instead of sharing indexes across cells (SETN-LR) (ablation)SETN · CIFAR-10 (with CutOut)test error (%): 2.81 -> 2.69Improved
use independent per-cell sampling (SETN) instead of sharing indexes across cells (SETN-LR) (ablation)SETN · CIFAR-100 (with CutOut)test error (%): 17.88 -> 17.25Improved
evaluate T=1K sampled candidates instead of arg max choice (T=1) (ablation)SETN · CIFAR-10 (with CutOut)test error (%): 3.41 -> 2.69Improved
evaluate T=1K sampled candidates instead of arg max choice (T=1) (ablation)SETN · CIFAR-100 (with CutOut)test error (%): 18.12 -> 17.25Improved
add CutOut augmentation (ablation)SETN (T=1K) · CIFAR-10test error (%): 3.56 -> 2.69Improved
add CutOut augmentation (ablation)SETN (T=1K) · CIFAR-100test error (%): 19.38 -> 17.25Improved
enlarge search space with two dilated convolutions (100x larger) (ablation)SETN · CIFAR-10test errorNo clear effect
use SETN-learned candidates instead of random candidates (ablation)SETN · one-shot candidate qualityone-shot validation accuracyImproved
use SETN instead of SETN-LR for candidate generation (ablation)SETN · one-shot candidate qualityone-shot validation accuracyMixed
use template-parameter validation accuracy to rank networks (ablation)SETN · pairwise ranking of 2000 networksranking agreement: >80% of pairs goodImproved

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