mlsanityData to 7 Oct 2026

Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition

arXiv 2302.06308 ↗First posted 13 Feb 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

In many machine learning tasks, a large general dataset and a small specialized dataset are available. In such situations, various domain adaptation methods can be used to adapt a general model to the target dataset. We show that in the case of neural networks trained for handwriting recognition using CTC, simple fine-tuning with data augmentation works surprisingly well in such scenarios and that it is resistant to overfitting even for very small target domain datasets. We evaluated the behavior of fine-tuning with respect to augmentation, training data size, and quality of the pre-trained network, both in writer-dependent and writer-independent settings. On a large real-world dataset, fine-tuning on new writers provided an average relative CER improvement of 25 % for 16 text lines and 50 % for 256 text lines.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

19 of 41 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  5. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  6. 2020Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognitioncited by 71
  7. 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
  8. 2021Rethinking Text Line Recognition Modelscited by 45
  9. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
  10. 2018An Efficient End-to-End Neural Model for Handwritten Text Recognitioncited by 25
  11. 2020Boosting offline handwritten text recognition in historical documents with few labeled linescited by 19
  12. 2022Multimodal Semi-Supervised Learning for Text Recognitioncited by 16
7 more
  1. 2019Adversarial Speaker Adaptationcited by 10
  2. 2019Speaker Adaptation for Attention-Based End-to-End Speech Recognitioncited by 10
  3. 2021AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptionscited by 10
  4. 2021TS-Net: OCR Trained to Switch Between Text Transcription Stylescited by 7
  5. 2021Mixed Model OCR Training on Historical Latin Script for Out-of-the-Box Recognition and Finetuningcited by 6
  6. 2022Self-Training of Handwritten Word Recognition for Synthetic-to-Real Adaptationcited by 5
  7. 2022Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2024LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Reportcited by 47
  2. 2025Handwritten Text Recognition: A Surveycited by 12
  3. 2025Practical Fine-Tuning of Autoregressive Models on Limited Handwritten Textscited by 1
  4. 2026Few-shot Writer Adaptation via Multimodal In-Context Learningcited by 1
  5. 2026OCR-Based Field Extraction for Archaeological Pottery Metadata: The CENTURIA Datasetcited by 0