AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

AutoSTR: Efficient Backbone Search for Scene Text Recognition

Hui Zhang, Quanming Yao, Mingkun Yang, Yongchao Xu, Xiang Bai

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 56 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 searched backbone (AutoSTR) instead of ASTER's fixed backboneASTER pipeline · IIIT5Kword accuracy: 93.3 -> 94.7Improved
add searched backbone (AutoSTR) instead of ASTER's fixed backboneASTER pipeline · IC15word accuracy: 78.5 -> 81.8Improved
add searched backbone (AutoSTR) instead of ASTER's fixed backboneASTER pipeline · IC13word accuracy: 91.5 -> 94.2Improved
add per-layer operation search instead of all MBConv(k:5,e:6) (ablation)AutoSTR · IC13word accuracy: 92.3 -> 94.2Improved
add per-layer operation search instead of all MBConv(k:5,e:6) (ablation)AutoSTR · IIIT5Kword accuracy: 94.5 -> 94.7Improved
add AutoSTR search instead of reusing DARTS cell (ablation)backbone · IIIT5Kword accuracy: 90.6 -> 94.7Improved
add AutoSTR search instead of reusing AutoDeepLab cell (ablation)backbone · SVTword accuracy: 87.2 -> 90.9Improved
use ABABB downsampling path instead of AABBB (ablation)AutoSTR operation search · IIIT5Kword accuracy: 93.9 -> 94.7Improved
add operation search (step 2) after path search with ABABB (ablation)AutoSTR · IIIT5Kword accuracy: 93.1 -> 94.7Improved
raise FLOPS regularizer beta from 0.0 to 0.9 (ablation)AutoSTR · IIIT5Kword accuracy and FLOPS: 94.6 -> 93.5 accuracy, 319 -> 149 FLOPS (M)Mixed
raise FLOPS regularizer beta from 0.0 to 0.6 (ablation)AutoSTR · IIIT5Kword accuracy: 94.6 -> 94.7 accuracy, 319 -> 256 FLOPS (M)No clear effect
use AutoSTR search instead of random architectures from the same space (ablation)AutoSTR · IIIT5Kword accuracy: 0.5%-1.4%Improved

Later papers that compared with this method

1 later accepted paper reports AutoSTR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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