SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition

TL;DR

SwinTextSpotter is a novel end-to-end scene text spotting framework that enhances the synergy between detection and recognition using a transformer-based approach and a Recognition Conversion mechanism, achieving superior performance without extra modules.

Contribution

The paper introduces a new unified framework with a Recognition Conversion mechanism that explicitly guides text localization through recognition loss, improving over simple backbone sharing methods.

Findings

Outperforms existing methods on multiple datasets

Does not require additional rectification modules

Handles arbitrarily-shaped and multi-lingual text effectively

Abstract

End-to-end scene text spotting has attracted great attention in recent years due to the success of excavating the intrinsic synergy of the scene text detection and recognition. However, recent state-of-the-art methods usually incorporate detection and recognition simply by sharing the backbone, which does not directly take advantage of the feature interaction between the two tasks. In this paper, we propose a new end-to-end scene text spotting framework termed SwinTextSpotter. Using a transformer encoder with dynamic head as the detector, we unify the two tasks with a novel Recognition Conversion mechanism to explicitly guide text localization through recognition loss. The straightforward design results in a concise framework that requires neither additional rectification module nor character-level annotation for the arbitrarily-shaped text. Qualitative and quantitative experiments on multi-oriented datasets RoIC13 and ICDAR 2015, arbitrarily-shaped datasets Total-Text and CTW1500, and multi-lingual datasets ReCTS (Chinese) and VinText (Vietnamese) demonstrate SwinTextSpotter significantly outperforms existing methods. Code is available at https://github.com/mxin262/SwinTextSpotter.