AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Neural Inheritance Relation Guided One-Shot Layer Assignment Search

Rang Meng, Weijie Chen, Di Xie, Yuan Zhang, Shiliang Pu

AAAI 2020 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 7 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 layer assignment with inherited sampling instead of using the handcrafted assignmentMobileNet-V1 · Tiny-ImageNetaccuracy: 1.42↑Improved
Search layer assignment with inherited sampling instead of using the handcrafted assignmentResNet-50 · Tiny-ImageNetaccuracy: 0.4↑Improved
Search layer assignment with inherited sampling instead of using the handcrafted assignmentMobileNet-V1 · ImageNetaccuracy: 71.32 vs 69.82Improved
Search layer assignment recursively from shallow to deep networksLayer assignment search · CIFAR-100accuracy: 68.35 vs 68.93; 72.98 vs 72.98Mixed
Use inherited sampling search rather than stand-alone training for the search stageMobileNet-V1 · ImageNetGPU-hours: 86.8 GPU-hours vs 173.9 GPU-hoursImproved

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