ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

TL;DR

ESTextSpotter introduces an explicit synergy mechanism within a Transformer framework for scene text spotting, modeling task-specific features for detection and recognition to significantly enhance performance.

Contribution

The paper proposes a novel explicit synergy approach with task-aware queries and a vision-language communication module, improving over implicit methods in scene text spotting.

Findings

Outperforms previous state-of-the-art methods

Significantly improves text detection and recognition accuracy

Demonstrates the effectiveness of explicit synergy in Transformer models

Abstract

In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent advances in Transformer-based methods usually adopt an implicit synergy strategy with shared query, which can not fully realize the potential of these two interactive tasks. In this paper, we argue that the explicit synergy considering distinct characteristics of text detection and recognition can significantly improve the performance text spotting. To this end, we introduce a new model named Explicit Synergy-based Text Spotting Transformer framework (ESTextSpotter), which achieves explicit synergy by modeling discriminative and interactive features for text detection and recognition within a single decoder. Specifically, we decompose the conventional shared query into task-aware queries for text polygon and content, respectively. Through the decoder with the proposed vision-language communication module, the queries interact with each other in an explicit manner while preserving discriminative patterns of text detection and recognition, thus improving performance significantly. Additionally, we propose a task-aware query initialization scheme to ensure stable training. Experimental results demonstrate that our model significantly outperforms previous state-of-the-art methods. Code is available at https://github.com/mxin262/ESTextSpotter.