References & Citations
Computer Science > Computer Vision and Pattern Recognition
Title: ODM: A Text-Image Further Alignment Pre-training Approach for Scene Text Detection and Spotting
(Submitted on 1 Mar 2024 (v1), last revised 17 Apr 2024 (this version, v2))
Abstract: 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 this https URL
Submission history
From: Pei Fu [view email][v1] Fri, 1 Mar 2024 06:13:53 GMT (6347kb,D)
[v2] Wed, 17 Apr 2024 12:05:28 GMT (6347kb,D)
Link back to: arXiv, form interface, contact.