AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Searching a High Performance Feature Extractor for Text Recognition Network

Hui Zhang, Quanming Yao, James Tin-Yau Kwok, Xiang Bai

TPAMI 2022 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 11 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
use TREFE instead of AutoSTRAutoSTR · IAMWER: 45.23 -> 16.41Improved
use TREFE instead of AutoSTRAutoSTR · RIMESWER: 20.40 -> 9.16Improved
use TREFE instead of AutoSTR (latency)AutoSTR · Scene textlatency (ms): 3.86 -> 2.62Improved
use TREFE instead of AutoSTRAutoSTR · IC15 (1811)word accuracy: 81.7 -> 84.0Improved
add searched spatial model instead of ResNet (ablation)TREFE with searched sequential model · IAMWER: 18.67 -> 16.41Improved
add searched spatial model instead of VGG (ablation)TREFE with searched sequential model · IAMWER: 20.80 -> 16.41Improved
use searched spatial model instead of DARTS CNN (ablation)TREFE with searched sequential model · IAMWER: 23.24 -> 16.41Improved
use searched sequential model instead of BiLSTM (ablation)TREFE with searched spatial model · IAMWER: 18.65 -> 16.41Improved
use searched sequential model instead of vanilla Transformer (ablation)TREFE with searched spatial model · IAMWER: 19.84 -> 16.41Improved
use searched sequential model instead of Evolved Transformer (ablation)TREFE with searched spatial model · IAMWER: 20.27 -> 16.41Improved
use NAS-searched TREFE instead of random search, no latency constraintrandom search · IAMWER: 17.04 -> 16.41Improved
use TREFE instead of random search at 2/3 latencyrandom search · IAMWER: 19.39 -> 19.18No clear effect

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