AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Are Labels Necessary for Neural Architecture Search?

Chenxi Liu, Piotr Dollár, Kaiming He, Ross Girshick, Alan Yuille, Saining Xie

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 73 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
search with rotation prediction instead of labelsDARTS · ImageNet-1K val (search IN1K)top-1 accuracy (%): 76.3 -> 75.8No clear effect
search with labels replaced by jigsaw (UnNAS)DARTS · ImageNet-1K val (search IN22K)top-1 accuracy (%): 75.9 -> 75.9No clear effect
search with colorization on Cityscapes instead of segmentation labelsDARTS · ImageNet-1K val (search Cityscapes)top-1 accuracy (%): 75.8 -> 75.2Hurt
search with jigsaw instead of segmentation labels on CityscapesDARTS · Cityscapes val mIoUmIoU (%): 72.4 -> 74.1Improved
search with unsupervised objectives instead of classification labels on IN22KDARTS · Cityscapes val mIoUmIoU (%): 72.4 -> 73.6Improved
search with colorization instead of classification labels on IN1KDARTS · Cityscapes val mIoUmIoU (%): 73.6 -> 72.2Hurt
search on IN22K instead of IN1K (10x more images)NAS/UnNAS DARTS · ImageNet-1K valtop-1 accuracy (%): 76.3 -> 75.9No clear effect
search with UnNAS on Cityscapes jigsaw instead of CIFAR-10 supervised proxy architectureDARTS · Cityscapes val mIoUmIoU (%): 72.6 -> 74.1Improved
use unsupervised pretext accuracy as proxy instead of CIFAR-10 supervised accuracy for rankingDARTS search space · rank correlation with ImageNet accuracySpearman rho: 0.90 -> ~0.8No 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