ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duan, Chen, Fu, Pei, Guo, Shan, Jiang, Qianyi, Wei, Xiaoming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909172304445440
author Duan, Chen
Fu, Pei
Guo, Shan
Jiang, Qianyi
Wei, Xiaoming
author_facet Duan, Chen
Fu, Pei
Guo, Shan
Jiang, Qianyi
Wei, Xiaoming
contents In recent years, text-image joint pre-training techniques have shown promising results in various tasks. However, in Optical Character Recognition (OCR) tasks, aligning text instances with their corresponding text regions in images poses a challenge, as it requires effective alignment between text and OCR-Text (referring to the text in images as OCR-Text to distinguish from the text in natural language) rather than a holistic understanding of the overall image content. In this paper, we propose a new pre-training method called OCR-Text Destylization Modeling (ODM) that transfers diverse styles of text found in images to a uniform style based on the text prompt. With ODM, we achieve better alignment between text and OCR-Text and enable pre-trained models to adapt to the complex and diverse styles of scene text detection and spotting tasks. Additionally, we have designed a new labeling generation method specifically for ODM and combined it with our proposed Text-Controller module to address the challenge of annotation costs in OCR tasks, allowing a larger amount of unlabeled data to participate in pre-training. Extensive experiments on multiple public datasets demonstrate that our method significantly improves performance and outperforms current pre-training methods in scene text detection and spotting tasks. Code is available at https://github.com/PriNing/ODM.
format Preprint
id arxiv_https___arxiv_org_abs_2403_00303
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
Duan, Chen
Fu, Pei
Guo, Shan
Jiang, Qianyi
Wei, Xiaoming
Computer Vision and Pattern Recognition
In recent years, text-image joint pre-training techniques have shown promising results in various tasks. However, in Optical Character Recognition (OCR) tasks, aligning text instances with their corresponding text regions in images poses a challenge, as it requires effective alignment between text and OCR-Text (referring to the text in images as OCR-Text to distinguish from the text in natural language) rather than a holistic understanding of the overall image content. In this paper, we propose a new pre-training method called OCR-Text Destylization Modeling (ODM) that transfers diverse styles of text found in images to a uniform style based on the text prompt. With ODM, we achieve better alignment between text and OCR-Text and enable pre-trained models to adapt to the complex and diverse styles of scene text detection and spotting tasks. Additionally, we have designed a new labeling generation method specifically for ODM and combined it with our proposed Text-Controller module to address the challenge of annotation costs in OCR tasks, allowing a larger amount of unlabeled data to participate in pre-training. Extensive experiments on multiple public datasets demonstrate that our method significantly improves performance and outperforms current pre-training methods in scene text detection and spotting tasks. Code is available at https://github.com/PriNing/ODM.
title ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.00303