AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search

Xin Chen, Yawen Duan, Zewei Chen, Hang Xu, Zihao Chen, Xiaodan Liang, Tong Zhang, Zhenguo Li

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 22 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 meta-training before searchCATCH · NAS-Bench-201accuracyImproved
add meta-training before search (CATCH-sfs vs CATCH-meta)CATCH · NAS-Bench-201 CIFAR-10accuracy: best model found in 280/500 trialsImproved
search from scratch without meta-trainingCATCH-sfs · NAS-Bench-201accuracyNo clear effect
use CATCH-meta instead of GDASone-shot NAS · NAS-Bench-201 CIFAR-100accuracy: 70.33 -> 72.57Improved
use CATCH-meta instead of R-NASone-shot NAS · NAS-Bench-201 CIFAR-10accuracy: 90.45 -> 91.33Improved
use CATCH-meta instead of ENASone-shot NAS · NAS-Bench-201 ImageNet16-120accuracy: 44.92 -> 46.07Improved
add context encoder (CATCH-zero uses z=0) (ablation)CATCH-meta · NAS-Bench-201search performanceImproved
use posterior context rather than random z (CATCH-random) (ablation)CATCH-meta · NAS-Bench-201 CIFAR-10 and CIFAR-100search performanceImproved
add context encoder (ablation)CATCH-meta · NAS-Bench-201 ImageNet16-120search performanceNo clear effect
transfer CATCH-Net-B found on ImageNet to COCO instead of searching on COCOCATCH-Net-B · COCOmAP: 42% mAP (vs 43.2 for CATCH-Net-C)Hurt

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