用语言模型提升模糊文本识别，端到端实现更准的场景文字检测。
TiCLS : Tightly Coupled Language Text Spotter
- 引入字符级预训练语言模型，显式融合语言知识
- 在ICDAR 2015和Total-Text上达到最优性能
- 适合处理碎片化或模糊的场景文字识别任务
场景文字检测旨在从真实图像中检测并识别文字，但实例常短小、断裂或视觉模糊。现有方法主要依赖视觉线索，隐式捕捉局部字符依赖，却忽视了外部语言知识的优势。此前尝试整合语言模型的方法要么未使用外部知识，要么采用与文字层级不匹配的预训练模型。我们提出TiCLS，一种端到端的文字检测器，显式引入字符级预训练语言模型（PLM）中的外部语言知识。TiCLS设计了语言解码器，融合视觉与语言特征，且可由预训练语言模型初始化，从而增强对模糊或断裂文字的鲁棒识别能力。在ICDAR 2015和Total-Text上的实验表明，TiCLS取得当前最优表现，验证了PLM引导的语言融合在场景文字检测中的有效性。
原文摘要 · Abstract (English)
Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local character dependencies, but they overlook the benefits of external linguistic knowledge. Prior attempts to integrate language models either adapt language modeling objectives without external knowledge or apply pretrained models that are misaligned with the word-level granularity of scene text. We propose TiCLS, an end-to-end text spotter that explicitly incorporates external linguistic knowledge from a character-level pretrained language model. TiCLS introduces a linguistic decoder that fuses visual and linguistic features, yet can be initialized by a pretrained language model, enabling robust recognition of ambiguous or fragmented text. Experiments on ICDAR 2015 and Total-Text demonstrate that TiCLS achieves state-of-the-art performance, validating the effectiveness of PLM-guided linguistic integration for scene text spotting.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。