面向少数民族文字的通用光学字符识别框架，解决低资源场景下识别难题
OmniOCR: Generalist OCR for Ethnic Minority Languages
- 采用动态低秩适配机制，按需分配模型容量以支持多语言
- 在藏文、水书等4个数据集上准确率提升39%-66%
- 适合处理稀缺标注、历史与现代文字混杂的少数民族语言
光学字符识别（OCR）虽随深度学习和多模态模型快速发展，但多数方法聚焦于拉丁文、中文等资源丰富文字。少数民族文字因书写系统复杂、标注稀少、历史与现代形式多样，导致低资源或零样本场景下的泛化困难。为此，我们提出OmniOCR——一个面向少数民族文字的通用识别框架。该框架引入动态低秩适配（Dynamic LoRA），按层和文字类型动态分配模型容量，实现高效适配同时保留知识。通过稀疏正则化剪枝冗余更新，确保适配过程紧凑且推理无额外开销。在TibetanMNIST、Shui、古彝文和Dongba四个数据集上的评估表明，OmniOCR优于零样本基线与标准微调，达到当前最佳准确率，相较最先进基线模型，准确率提升39%至66%。代码已开源：https://github.com/AIGeeksGroup/OmniOCR。
原文摘要 · Abstract (English)
Optical character recognition (OCR) has advanced rapidly with deep learning and multimodal models, yet most methods focus on well-resourced scripts such as Latin and Chinese. Ethnic minority languages remain underexplored due to complex writing systems, scarce annotations, and diverse historical and modern forms, making generalization in low-resource or zero-shot settings challenging. To address these challenges, we present OmniOCR, a universal framework for ethnic minority scripts. OmniOCR introduces Dynamic Low-Rank Adaptation (Dynamic LoRA) to allocate model capacity across layers and scripts, enabling effective adaptation while preserving knowledge.A sparsity regularization prunes redundant updates, ensuring compact and efficient adaptation without extra inference cost. Evaluations on TibetanMNIST, Shui, ancient Yi, and Dongba show that OmniOCR outperforms zero-shot foundation models and standard post training, achieving state-of-the-art accuracy with superior parameter efficiency, and compared with the state-of-the-art baseline models, it improves accuracy by 39%-66% on these four datasets. Code: https://github.com/AIGeeksGroup/OmniOCR.
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。