Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning

TL;DR

This paper introduces Hi-GITA, a hierarchical multi-granularity image-text aligning framework for zero-shot Chinese character recognition, leveraging detailed semantic information to improve accuracy significantly over existing methods.

Contribution

The paper proposes a novel hierarchical multi-granularity encoding and contrastive alignment approach for zero-shot CCR, capturing detailed semantic cues at multiple levels.

Findings

Achieves about 20% accuracy improvement in handwritten character zero-shot recognition.

Outperforms existing zero-shot CCR methods significantly.

Demonstrates effectiveness of multi-granularity semantic modeling.

Abstract

Chinese Character Recognition (CCR) is a fundamental technology for intelligent document processing. Unlike Latin characters, Chinese characters exhibit unique spatial structures and compositional rules, allowing for the use of fine-grained semantic information in representation. However, existing approaches are usually based on auto-regressive as well as edit distance post-process and typically rely on a single-level character representation. In this paper, we propose a Hierarchical Multi-Granularity Image-Text Aligning (Hi-GITA) framework based on a contrastive paradigm. To leverage the abundant fine-grained semantic information of Chinese characters, we propose multi-granularity encoders on both image and text sides. Specifically, the Image Multi-Granularity Encoder extracts hierarchical image representations from character images, capturing semantic cues from localized strokes to holistic structures. The Text Multi-Granularity Encoder extracts stroke and radical sequence representations at different levels of granularity. To better capture the relationships between strokes and radicals, we introduce Multi-Granularity Fusion Modules on the image and text sides, respectively. Furthermore, to effectively bridge the two modalities, we further introduce a Fine-Grained Decoupled Image-Text Contrastive loss, which aligns image and text representations across multiple granularities. Extensive experiments demonstrate that our proposed Hi-GITA significantly outperforms existing zero-shot CCR methods. For instance, it brings about 20% accuracy improvement in handwritten character and radical zero-shot settings. Code and models will be released soon.