# Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing

arXiv: https://arxiv.org/abs/2411.15585 · HTML: https://mlsanity.com/paper/2411.15585/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 55 references that are in the map.
- First posted on arXiv 23 Nov 2024.

## Builds on (most cited first, 30 of 33)

- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Synthetic Data for Text Localisation in Natural Images](https://mlsanity.com/paper/1604.06646/) (2016)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition](https://mlsanity.com/paper/2103.06495/) (2021)
- [Scene Text Recognition with Permuted Autoregressive Sequence Models](https://mlsanity.com/paper/2207.06966/) (2022)
- [ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)](https://mlsanity.com/paper/1909.07145/) (2019)
- [Towards Accurate Scene Text Recognition with Semantic Reasoning Networks](https://mlsanity.com/paper/2003.12294/) (2020)
- [Semi-Supervised Learning with Generative Adversarial Networks](https://mlsanity.com/paper/1606.01583/) (2016)
- [From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network](https://mlsanity.com/paper/2108.09661/) (2021)
- [Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks](https://mlsanity.com/paper/1511.06390/) (2015)
- [SVTR: Scene Text Recognition with a Single Visual Model](https://mlsanity.com/paper/2205.00159/) (2022)
- [RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition](https://mlsanity.com/paper/2007.07542/) (2020)
- [ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification](https://mlsanity.com/paper/1812.05824/) (2018)
- [What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels](https://mlsanity.com/paper/2103.04400/) (2021)
- [Symmetry-constrained Rectification Network for Scene Text Recognition](https://mlsanity.com/paper/1908.01957/) (2019)
- [Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition](https://mlsanity.com/paper/2208.00438/) (2022)
- [Revisiting Scene Text Recognition: A Data Perspective](https://mlsanity.com/paper/2307.08723/) (2023)
- [Multi-Granularity Prediction for Scene Text Recognition](https://mlsanity.com/paper/2209.03592/) (2022)
- [Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features](https://mlsanity.com/paper/2111.15263/) (2021)
- [Semi-Supervised Learning with Context-Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1611.06430/) (2016)
- [Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition](https://mlsanity.com/paper/2305.05140/) (2023)
- [Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition](https://mlsanity.com/paper/2209.00641/) (2022)
- [Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition](https://mlsanity.com/paper/2310.04999/) (2023)
- [LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition](https://mlsanity.com/paper/2308.12774/) (2023)

## Built on by (most cited first, 2 of 2)

- [IGD: Instructional Graphic Design with Multimodal Layer Generation](https://mlsanity.com/paper/2507.09910/) (2025)
- [What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution](https://mlsanity.com/paper/2602.06450/) (2026)

## Abstract (arXiv)

Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the monotonousness of widely used synthetic training data and the sensitivity of the model to character morphologies. To address these issues, inspired by the human learning process of viewing and summarizing, we facilitate the contrastive learning-based STR framework in a self-motivated manner by leveraging synthetic and real unlabeled data without any human cost. In the viewing process, to compensate for the simplicity of synthetic data and enrich character morphology diversity, we propose an Online Generation Strategy to generate background-free samples with diverse character styles. By excluding background noise distractions, the model is encouraged to focus on character morphology and generalize the ability to recognize complex samples when trained with only simple synthetic data. To boost the summarizing process, we theoretically demonstrate the derivation error in the previous character contrastive loss, which mistakenly causes the sparsity in the intra-class distribution and exacerbates ambiguity on challenging samples. Therefore, a new Character Unidirectional Alignment Loss is proposed to correct this error and unify the representation of the same characters in all samples by aligning the character features in the student model with the reference features in the teacher model. Extensive experiment results show that our method achieves SOTA performance (94.7% and 70.9% average accuracy on common benchmarks and Union14M-Benchmark). Code will be available at https://github.com/qqqyd/ViSu.