Cross-Lingual Learning in Multilingual Scene Text Recognition

Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
12/17/2023
cs.CV

Official code: ku21fan/CLL-STR (19 stars, MIT, last commit 2024-09-29).

Abstract

In this paper, we investigate cross-lingual learning (CLL) for multilingual scene text recognition (STR). CLL transfers knowledge from one language to another. We aim to find the condition that exploits knowledge from high-resource languages for improving performance in low-resource languages. To do so, we first examine if two general insights about CLL discussed in previous works are applied to multilingual STR: (1) Joint learning with high- and low-resource languages may reduce performance on low-resource languages, and (2) CLL works best between typologically similar languages. Through extensive experiments, we show that two general insights may not be applied to multilingual STR. After that, we show that the crucial condition for CLL is the dataset size of high-resource languages regardless of the kind of high-resource languages. Our code, data, and models are available at https://github.com/ku21fan/CLL-STR.

View on arXivView PDF

Code Implementations(1)

ku21fan/CLL-STROfficial100%
MIT

Cross-lingual learning in scene text recognition (ICASSP2024)

191Python, Jupyter Notebook2 years agoMIT
cross-lingual-learningicassp2024multilingualmultilingual-text-recognitionocr+2 more

Similar Papers

Unsupervised Cross-lingual Representation Learning at Scale

86% match2 repos2.9k2019

Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment

85% match1 repo72023

T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification

85% match1 repo52023

Analysing Cross-Lingual Transfer in Low-Resourced African Named Entity Recognition

85% match1 repo72023

Automatic Discrimination of Human and Neural Machine Translation in Multilingual Scenarios

85% match2023

How Do Multilingual Encoders Learn Cross-lingual Representation?

84% match2022

Cite this paper

@article{baek2023crosslingual,
  title  = {Cross-Lingual Learning in Multilingual Scene Text Recognition},
  author = {Jeonghun Baek and Yusuke Matsui and Kiyoharu Aizawa},
  year   = {2023},
  eprint = {2312.10806},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2312.10806v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2312.10806.svg)](https://codeofpaper.com/paper/2312.10806)

Discussion