Exploring Style-Robust Scene Text Detection via Style-Aware Learning

Abstract

Although current scene text detectors achieve remarkable accuracy across different and diverse styles of datasets by fine-tuning models multiple times, these approaches are time-consuming and hinder model generalization. As such, exploring a training strategy that only requires training once on all datasets is a promising solution. However, the text-style mismatch poses challenges to accuracy in such an approach. To mitigate these issues, we propose a style-aware learning network (SLNText) for style-robust text detection in the wild. This includes a style-aware head to distinguish the text styles of images and a dynamic selection head to realize the detection of images with different text styles. SLNText is only trained once, achieving superior performance by automatically learning from multiple text styles and overcoming the style mismatch issue inherent in one-size-fits-all approaches. By using only one set of network parameters, our method significantly reduces the training consumption while maintaining a satisfactory performance on several styles of datasets. Our extensive experiments demonstrate that SLNText achieves satisfactory performance in several styles of datasets, showcasing its effectiveness and efficiency as a promising solution to style-robust scene text detection.

Keywords

• scene text detection
• style-aware learning
• dynamic selection head
• dynamic training strategy