AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Angle-based Search Space Shrinking for Neural Architecture Search

Yiming Hu, Yuding Liang, Zichao Guo, Ruosi Wan, Xiangyu Zhang, Yichen Wei, Qingyi Gu, Jian Sun

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 64 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
apply ABS shrinking before searchFairNAS · ImageNet, MobileNet-like spacetop-1 accuracy: 74.24% -> 74.42%Improved
apply ABS shrinking before searchSPOS · ImageNet, MobileNet-like spacetop-1 accuracy: 75.33% -> 75.97%Improved
apply ABS shrinking before searchProxylessNAS · ImageNet, MobileNet-like spacetop-1 accuracy: 75.56% -> 76.14%Improved
apply ABS shrinking before searchDARTS · ImageNet, DARTS spacetop-1 accuracy: 73.39% -> 75.59Improved
apply ABS shrinking before searchPDARTS · ImageNet, DARTS spacetop-1 accuracy: 75.02% -> 75.89Improved
scale channels down to 45 to match FLOPs after ABSDARTS+ABS and PDARTS+ABS · ImageNet, DARTS spacetop-1 accuracy: DARTS 75.59 -> 75.19; PDARTS 75.89 -> 75.64 (still above baselines 73.39%, 75.02%)No clear effect
use angle metric instead of accuracy (Re-BN) to rank child models (ablation)supernet ranking · NAS-Bench-201 CIFAR-10Kendall's Tau: 0.5436 -> 0.5748Improved
use angle metric instead of accuracy (Re-BN) to rank child models (ablation)supernet ranking · NAS-Bench-201 CIFAR-100Kendall's Tau: 0.5329 -> 0.6040Improved
use angle metric instead of accuracy (Re-BN) to rank child models (ablation)supernet ranking · NAS-Bench-201 ImageNet-16-120Kendall's Tau: 0.5391 -> 0.5445Improved
use angle metric instead of accuracy metric for computing child model scores (ablation)metric computation · NAS-Bench-201 CIFAR-10processing time (s): 561.75 -> 0.92Improved
change weight initialization (Kaiming, Xavier, orthogonal) (ablation)angle metric · NAS-Bench-201 CIFAR-10Kendall's Tau: 0.622 / 0.609 / 0.609No clear effect
use ABS-found shrunk space instead of human-designed best space S8 (ablation)five NAS algorithms · NAS-Bench-201 CIFAR-100accuracy: DARTS 65.70% -> 67.57%; SETN 70.12% -> 69.12%; GDAS 71.01% -> 70.35%; SPOS 70.49% -> 71.95%Mixed

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