Abstract
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: this https URL.
Abstract (translated)
光学字符识别（OCR）技术在深度学习和多模态模型的推动下迅速发展，然而大多数方法主要集中在资源丰富的文字系统上，如拉丁语系和中文。由于书写系统的复杂性、标注数据的稀缺以及历史与现代形式的多样性，少数民族语言的OCR技术进展缓慢，并且在低资源或零样本设置下的泛化能力面临挑战。为了解决这些问题，我们提出了OmniOCR——一个用于处理少数民族文字的通用框架。 OmniOCR引入了动态低秩适配（Dynamic Low-Rank Adaptation, Dynamic LoRA）机制，在不同层和书写系统之间分配模型容量，从而能够有效地进行适应同时保留知识。此外，稀疏正则化通过剪枝冗余更新来确保高效且紧凑的适应过程，并不会增加额外的推理成本。 在藏文MNIST、水语、古彝文以及东巴文字上的评估表明，OmniOCR不仅超越了零样本基础模型和标准后训练方法，在参数效率方面达到了最新的技术水平。与当前最先进的基线模型相比，它在这四个数据集上分别提高了39%-66%的准确性。 代码链接：[这个 URL](https://this-url.com)
URL
https://arxiv.org/abs/2602.21042
