OmniOCR: Generalist OCR for Ethnic Minority Languages
This addresses the underexplored issue of OCR for low-resource ethnic minority languages, offering a novel adaptation method that is incremental in advancing multilingual OCR capabilities.
The paper tackles the problem of optical character recognition for ethnic minority languages, which face challenges like complex scripts and scarce data, by introducing OmniOCR with Dynamic LoRA and sparsity regularization, achieving state-of-the-art accuracy improvements of 39%-66% on four datasets while maintaining parameter efficiency.
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.