Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition

TL;DR

This paper introduces a progressive few-shot learning method for low-resource handwritten text recognition, reducing annotation effort by using synthetic pretraining and unsupervised pseudo-labeling, achieving competitive results.

Contribution

It presents a novel progressive learning approach combining synthetic pretraining and unsupervised pseudo-labeling for efficient low-resource handwritten text recognition.

Findings

Achieves competitive recognition accuracy with minimal human annotation.

Reduces annotation effort significantly through pseudo-labeling.

Effective across different manuscript datasets.

Abstract

Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. The main difficulty comes from the very few annotated data and the limited linguistic information (e.g. dictionaries and language models). Thus, we propose a few-shot learning-based handwriting recognition approach that significantly reduces the human labor annotation process, requiring only few images of each alphabet symbol. The method consists in detecting all the symbols of a given alphabet in a textline image and decoding the obtained similarity scores to the final sequence of transcribed symbols. Our model is first pretrained on synthetic line images generated from any alphabet, even though different from the target domain. A second training step is then applied to diminish the gap between the source and target data. Since this retraining would require annotation of thousands of handwritten symbols together with their bounding boxes, we propose to avoid such human effort through an unsupervised progressive learning approach that automatically assigns pseudo-labels to the non-annotated data. The evaluation on different manuscript datasets show that our model can lead to competitive results with a significant reduction in human effort. The code will be publicly available in this repository: \url{https://github.com/dali92002/HTRbyMatching}