Publication Details
Self-supervised Pre-training of Text Recognizers
Self-supervised learning, Text Recognition, Pre-training, OCR, HTR
In this paper, we investigate self-supervised pre-training methods for document
text recognition. Nowadays, large unlabeled datasets can be collected for many
research tasks, including text recognition, but it is costly to annotate them.
Therefore, methods utilizing unlabeled data are researched. We study
self-supervised pre-training methods based on masked label prediction using three
different approaches - Feature Quantization, VQ-VAE, and Post-Quantized AE. We
also investigate joint-embedding approaches with VICReg and NT-Xent objectives,
for which we propose an image shifting technique to prevent model collapse where
it relies solely on positional encoding while completely ignoring the input
image. We perform our experiments on historical handwritten (Bentham) and
historical printed datasets mainly to investigate the benefits of the
self-supervised pre-training techniques with different amounts of annotated
target domain data. We use transfer learning as strong baselines. The evaluation
shows that the self-supervised pretraining on data from the target domain is very
effective, but it struggles to outperform transfer learning from closely related
domains. This paper is one of the first researches exploring self-supervised
pre-training in document text recognition, and we believe that it will become
a cornerstone for future research in this area. We made our implementation of the
investigated methods publicly available at
https://github.com/DCGM/pero-pretraining.
@inproceedings{BUT193312,
author="Martin {Kišš} and Michal {Hradiš}",
title="Self-supervised Pre-training of Text Recognizers",
booktitle="Barney Smith, E.H., Liwicki, M., Peng, L. (eds) Document Analysis and Recognition - ICDAR 2024",
year="2024",
series="Lecture Notes in Computer Science",
volume="14807",
pages="218--235",
publisher="Springer Nature Switzerland AG",
address="Atény",
doi="10.1007/978-3-031-70546-5\{_}13",
isbn="978-3-031-70545-8",
url="https://link.springer.com/chapter/10.1007/978-3-031-70546-5_13"
}