AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-Supervised Learning for Text Recognition: A Critical Survey

Carlos Penarrubia, Jose J. Valero-Mas, Jorge Calvo-Zaragoza

IJCV 2025 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 19 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 SSL-pretrained ViT (SSM-Small) instead of CNN SSL (SimAN)self-supervised text recognition · STR average WAccWAcc: 77.3 -> 93.8Improved
scale DiG from Tiny to BaseDiG · STR average WAccWAcc: 90.6 -> 92.9Improved
scale CCD from Tiny to BaseCCD · STR average WAccWAcc: 92.6 -> 94.0Improved
use attention decoder instead of CTC in PerSec-ViTPerSec-ViT · STR average WAccWAcc: 76.3 -> 79.2Improved
use attention decoder instead of CTC in PerSec-CNNPerSec-CNN · STR average WAccWAcc: 74.9 -> 77.6Improved
increase pre-training data (Text-DIAE 4M versus DiG/CCD 32.77M)MIM pre-training · IIITWAcc: 86.1 -> 96.7Improved
add SSL pre-training before fine-tuning on real data versus from scratch (ablation)text recognizers · STR average, ARD real data fine-tuningWAccImproved
add SSL pre-training before fine-tuning on synthetic data versus from scratch (ablation)text recognizers · STR average, synthetic data fine-tuningWAccImproved

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