Saved in:
Bibliographic Details
Main Authors: Kohút, Jan, Hradiš, Michal
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2302.06308
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912353943027712
author Kohút, Jan
Hradiš, Michal
author_facet Kohút, Jan
Hradiš, Michal
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2302_06308
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition
Kohút, Jan
Hradiš, Michal
Computer Vision and Pattern Recognition
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.
title Fine-tuning Is a Surprisingly Effective Domain Adaptation Baseline in Handwriting Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2302.06308