# The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing

arXiv: https://arxiv.org/abs/2506.06761 · HTML: https://mlsanity.com/paper/2506.06761/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 68 references that are in the map.
- First posted on arXiv 7 Jun 2025.

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://mlsanity.com/paper/1909.12488/) (2019)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models](https://mlsanity.com/paper/2305.12827/) (2023)
- [TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text](https://mlsanity.com/paper/2105.05486/) (2021)
- [ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019](https://mlsanity.com/paper/1907.00945/) (2019)
- [Towards End-to-End Unified Scene Text Detection and Layout Analysis](https://mlsanity.com/paper/2203.15143/) (2022)
- [Vision Transformer for Fast and Efficient Scene Text Recognition](https://mlsanity.com/paper/2105.08582/) (2021)
- [Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition](https://mlsanity.com/paper/1903.07377/) (2019)
- [Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1908.00262/) (2019)
- [On Vocabulary Reliance in Scene Text Recognition](https://mlsanity.com/paper/2005.03959/) (2020)
- [Primitive Representation Learning for Scene Text Recognition](https://mlsanity.com/paper/2105.04286/) (2021)
- [Full Page Handwriting Recognition via Image to Sequence Extraction](https://mlsanity.com/paper/2103.06450/) (2021)
- [A Survey of Historical Document Image Datasets](https://mlsanity.com/paper/2203.08504/) (2022)
- [Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition](https://mlsanity.com/paper/2107.10064/) (2021)
- [Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation](https://mlsanity.com/paper/2411.11295/) (2024)
- [Convolutional Neural Networks for Automatic Meter Reading](https://mlsanity.com/paper/1902.09600/) (2019)
- [Standard Language Ideology in AI-Generated Language](https://mlsanity.com/paper/2406.08726/) (2024)
- [MC2: Towards Transparent and Culturally-Aware NLP for Minority Languages in China](https://mlsanity.com/paper/2311.08348/) (2023)
- [An Interpretable Deep Learning Approach for Morphological Script Type Analysis](https://mlsanity.com/paper/2408.11150/) (2024)
- [Sequence to Sequence Learning for Optical Character Recognition](https://mlsanity.com/paper/1511.04176/) (2015)
- [FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition](https://mlsanity.com/paper/2007.11462/) (2020)

## Built on by (most cited first, 1 of 1)

- [Unapologetically Distributed: A Call for Decentralized Document Analysis](https://mlsanity.com/paper/2609.39684/) (2026)

## Abstract (arXiv)

Achieving robustness in recognition systems across diverse domains is crucial for their practical utility. While ample data availability is usually assumed, low-resource languages, such as ancient manuscripts and non-western languages, tend to be kept out of the equations of massive pretraining and foundational techniques due to an under representation. In this work, we aim for building models which can generalize to new distributions of data, such as alphabets, faster than centralized fine-tune strategies. For doing so, we take advantage of the recent advancements in model editing to enhance the incorporation of unseen scripts (low-resource learning). In contrast to state-of-the-art meta-learning, we showcase the effectiveness of domain merging in sparse distributions of data, with agnosticity of its relation to the overall distribution or any other prototyping necessity. Even when using the same exact training data, our experiments showcase significant performance boosts in transfer learning to new alphabets and out-of-domain evaluation in challenging domain shifts, including historical ciphered texts and non-Latin scripts. This research contributes a novel approach into building models that can easily adopt under-represented alphabets and, therefore, enable document recognition to a wider set of contexts and cultures.