# One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition

arXiv: https://arxiv.org/abs/2105.05300 · HTML: https://mlsanity.com/paper/2105.05300/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 11 May 2021.

## Builds on (most cited first, 12 of 12)

- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [FIGR: Few-shot Image Generation with Reptile](https://mlsanity.com/paper/1901.02199/) (2019)
- [Few-shot Compositional Font Generation with Dual Memory](https://mlsanity.com/paper/2005.10510/) (2020)
- [Generating Handwritten Chinese Characters using CycleGAN](https://mlsanity.com/paper/1801.08624/) (2018)
- [A Deep Factorization of Style and Structure in Fonts](https://mlsanity.com/paper/1910.00748/) (2019)
- [A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition](https://mlsanity.com/paper/2009.12577/) (2020)
- [Selective Style Transfer for Text](https://mlsanity.com/paper/1906.01466/) (2019)
- [Adaptive Text Recognition through Visual Matching](https://mlsanity.com/paper/2009.06610/) (2020)
- [Decipherment of Historical Manuscript Images](https://mlsanity.com/paper/1810.04297/) (2018)

## Built on by (most cited first, 6 of 6)

- [OCR-IDL: OCR Annotations for Industry Document Library Dataset](https://mlsanity.com/paper/2202.12985/) (2022)
- [How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning](https://mlsanity.com/paper/2305.02593/) (2023)
- [Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniques](https://mlsanity.com/paper/2507.06275/) (2025)
- [Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?](https://mlsanity.com/paper/2508.09936/) (2025)
- [Character Recognition in Byzantine Seals with Deep Neural Networks](https://mlsanity.com/paper/2401.10741/) (2024)
- [Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes](https://mlsanity.com/paper/2609.16859/) (2026)

## Abstract (arXiv)

Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). For example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the message contents. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol in the alphabet. After generating symbols, we create synthetic lines to train state-of-the-art HTR architectures in a segmentation free fashion. Quantitative and qualitative analyses were carried out and confirm the effectiveness of the proposed method.