AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

MixPath: A Unified Approach for One-shot Neural Architecture Search

Xiangxiang Chu, Shun Lu, Xudong Li, Bo Zhang

ICCV 2023 · Architectures and efficiency › Neural architecture search · approach: One-shot and few-shot supernets · 33 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
add shadow batch normalization (SBN) to multi-path supernet training (ablation)MixPath supernet (m=4) · NAS-Bench-101 subsetKendall tau (no calibration): 0.117 -> 0.393Improved
add BN post-calibration on top of SBN (ablation)MixPath supernet (m=4) · NAS-Bench-101 subsetKendall tau: 0.393 -> 0.597Improved
use linear (m) SBNs instead of exponential SBNs with calibration (ablation)MixPath supernet (m=3) · NAS-Bench-101 subsetKendall tau (with calibration): 0.34 -> 0.59Improved
use exponential SBNs instead of linear when no calibration is applied (ablation)MixPath supernet (m=3) · NAS-Bench-101 subsetKendall tau (no calibration): 0.32 -> 0.37Improved
replace simple feature magnitude scaling with SBNs (ablation)MixPath supernet (m=4) · NAS-Bench-101 subsetKendall tau (with calibration): 0.472 -> 0.597Improved
train with SBN in the full search pipeline (ablation)MixPath on CIFAR-10 S1 · CIFAR-10, under 500M FLOPStop-1 accuracy (%): 97.12 -> 97.44Improved
use MixPath multi-path supernet instead of SPOS for branch compositionNAS-Bench-101 m=4 branch composition · NAS-Bench-101Kendall tau: -0.225 -> 0.504Improved
use MixPath instead of DARTS in reduced NAS-Bench-101NAS-Bench-101 S4 · Reduced NAS-Bench-101top-1 accuracy (%): 79.42 -> 94.22Improved
use NSGA-II search instead of random search (ablation)MixPath supernet S3 · ImageNet Pareto frontaccuracy and FLOPs of elite modelsImproved
swap MixNet-M for MixPath-A backboneRetinaNet · COCO val2017AP (%): 31.3 -> 31.5Improved

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