HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition
This addresses challenges in Chinese text recognition for applications like on-device deployment, offering a novel solution for handling complex scripts and OOV characters.
The paper tackled the problem of Chinese text recognition by proposing HierCode, a lightweight hierarchical codebook that enables zero-shot recognition of out-of-vocabulary characters and achieves state-of-the-art performance across diverse benchmarks with fewer parameters and faster inference.
Text recognition, especially for complex scripts like Chinese, faces unique challenges due to its intricate character structures and vast vocabulary. Traditional one-hot encoding methods struggle with the representation of hierarchical radicals, recognition of Out-Of-Vocabulary (OOV) characters, and on-device deployment due to their computational intensity. To address these challenges, we propose HierCode, a novel and lightweight codebook that exploits the innate hierarchical nature of Chinese characters. HierCode employs a multi-hot encoding strategy, leveraging hierarchical binary tree encoding and prototype learning to create distinctive, informative representations for each character. This approach not only facilitates zero-shot recognition of OOV characters by utilizing shared radicals and structures but also excels in line-level recognition tasks by computing similarity with visual features, a notable advantage over existing methods. Extensive experiments across diverse benchmarks, including handwritten, scene, document, web, and ancient text, have showcased HierCode's superiority for both conventional and zero-shot Chinese character or text recognition, exhibiting state-of-the-art performance with significantly fewer parameters and fast inference speed.