AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Pushing the Performance Limit of Scene Text Recognizer Without Human Annotation

Caiyuan Zheng, Hui Li, Seon-Min Rhee, Seungju Han, Jae-Joon Han, Peng Wang

CVPR 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 20 citations (OpenAlex)

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
Apply consistency regularization using unlabeled real imagesCRNN, MORAN, HGA, and TRBA · STR benchmarks (Avg)accuracy: CRNN: 82.8% to 85.9%; MORAN: 88.5% to 90.2%; HGA: 88.7% to 91.2%; TRBA: 91.5% to 94.5%Improved
Use consistency regularization with 10% synthetic labeled and 10% real unlabeled dataTRBA · STR benchmarks (Avg)accuracy: 93.2%Improved
Use FixMatch on same-domain labeled and unlabeled dataTRBA · In-domain RLaccuracy: +3.6%Improved
Use UDA on same-domain labeled and unlabeled dataTRBA · In-domain RLaccuracy: +2.6%Improved
Use FixMatch with synthetic labeled and real unlabeled dataTRBA · Cross-domain SLsm and RUsmaccuracy: 11.0%Hurt
Use UDA with synthetic labeled and real unlabeled dataTRBA · Cross-domain SLsm and RUsmaccuracy: 4.6%Hurt
Add a projection layer before the classifier (ablation)TRBA consistency framework · STR benchmarks (Avg)accuracy: +0.7% (87.0% to 87.7%)Improved
Add weight decay to the projection-layer variant (ablation)TRBA consistency framework · STR benchmarks (Avg)accuracy: +3.5% (87.7% to 91.2%)Improved
Add EMA to the projection-plus-weight-decay variant (ablation)TRBA consistency framework · STR benchmarks (Avg)accuracy: +1.6%Improved
Add domain adaptation to the projection-plus-weight-decay-plus-EMA variant (ablation)TRBA consistency framework · STR benchmarks (Avg)accuracy: 92.8% to 93.2%Improved
Use character-level consistency regularization instead of standard consistency regularization (ablation)TRBA · STR benchmarks (Avg)accuracy: 92.2% to 93.2%; 1%Improved
Replace KL-divergence with MSE for consistency loss (ablation)TRBA · STR benchmarks (Avg)accuracy: 93.2% to 91.0%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