AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Evolving Search Space for Neural Architecture Search

Yuanzheng Ci, Chen Lin, Ming Sun, Boyu Chen, Hongwen Zhang, Wanli Ouyang

ICCV 2021 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 44 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 the 27 OPs space with NSE instead of ProxylessNASProxylessNAS · ImageNet (27 OPs space)top-1 accuracy (%): 74.5 -> 75.0Improved
search the 27 OPs space with NSE instead of One-ShotOne-Shot · ImageNet (27 OPs space)top-1 accuracy (%): 73.5 -> 75.0Improved
enlarge ProxylessNAS search space from manual 6 OPs to 27 OPsProxylessNAS · ImageNettop-1 accuracy (%): 74.6 -> 74.5No clear effect
use random 6 OPs subsets instead of manual 6 OPs spaceProxylessNAS · ImageNettop-1 accuracy (%): 74.6 -> 74.2Hurt
add a second search space after the 27 OPs space (ablation)NSE · ImageNet (FLOPs-constrained)top-1 accuracy (%): 75.3 -> 75.5Improved
add SE and swish modules to the searched networkNSENet · ImageNet (FLOPs-constrained)top-1 accuracy (%): 75.5 -> 77.3Improved
use NSE with latency constraint instead of PC-NAS-L in the same spacePC-NAS-L · ImageNet (latency-constrained)top-1 accuracy (%): 77.5 -> 77.9, 10.3 ms -> 8.9 msImproved
swap EfficientNet-B0 backbone for NSENetEfficientDet-D0 · COCOmAP: 33.8 -> 34.5Improved
swap MobileNetV2 backbone for NSENetEfficientDet-D0 · COCOmAP: 32.7 -> 34.5Improved
enlarge initial layer-wise search space from K=5 to K=9 without evolution (ablation)NSE with simplification · ImageNet (retrain accuracy)top-1 accuracy (%)Hurt
add Lock and Rehearse (ablation)NSE (K=9) · ImageNet (retrain accuracy)top-1 accuracy (%)Improved
add search space simplification and Pareto aggregation (ablation)NSE round 1 (K=5) · ImageNet (50-epoch retrain accuracy)top-1 accuracy (%)Improved

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