Abstract
Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Synthetic data offers a cost-effective and perfectly labeled alternative. However, its performance often lags behind, revealing a significant domain gap between real and current synthetic data. In this work, we systematically analyze mainstream rendering-based synthetic datasets and identify their key limitations: insufficient diversity in corpus, font, and layout, which restricts their realism in complex scenarios. To address these issues, we introduce UnionST, a strong data engine synthesizes text covering a union of challenging samples and better aligns with the complexity observed in the wild. We then construct UnionST-S, a large-scale synthetic dataset with improved simulations in challenging scenarios. Furthermore, we develop a self-evolution learning (SEL) framework for effective real data annotation. Experiments show that models trained on UnionST-S achieve significant improvements over existing synthetic datasets. They even surpass real-data performance in certain scenarios. Moreover, when using SEL, the trained models achieve competitive performance by only seeing 9% of real data labels.
Abstract (translated)
大规模且类别平衡的文本数据对于训练有效的场景文字识别（STR）模型至关重要，但在实际收集这类数据时非常困难。合成数据提供了一种成本效益高且标注完美的替代方案。然而，其性能通常落后于真实数据，显示出当前合成数据与现实之间存在显著差距。在这项工作中，我们系统地分析了主流的基于渲染的合成数据集，并确定了它们的关键限制：文本语料库、字体和布局多样性不足，这在复杂场景中限制了它们的真实感。为了解决这些问题，我们引入了UnionST，这是一种强大的数据引擎，它综合生成具有挑战性的样本并更好地与现实世界中的复杂性对齐。然后，我们构建了UnionST-S，这是一个大规模的合成数据集，在具有挑战性的场景中提供了改进的模拟效果。此外，我们还开发了一种自我进化学习（SEL）框架，用于有效的真实数据标注。实验表明，基于UnionST-S训练的模型在现有合成数据集上取得了显著的进步，并且在某些情况下甚至超过了真实数据的表现。另外，在使用SEL时，仅通过9%的真实数据标签进行训练，所得到的模型就能实现具有竞争力的性能。
URL
https://arxiv.org/abs/2602.06450
