Skip to yearly menu bar Skip to main content


Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer

Zhen Zhao · Jingqun Tang · Chunhui Lin · Binghong Wu · Can Huang · Hao Liu · Xin Tan · Zhizhong Zhang · Yuan Xie

Arch 4A-E Poster #93
[ ] [ Project Page ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT

Abstract: Scene text recognition (STR) in the wild frequently encounters challenges when coping with domain variations, font diversity, shape deformations, etc. A straightforward solution is performing model fine-tuning tailored to a specific scenario, but it is computationally intensive and requires multiple model copies for various scenarios. Recent studies indicate that large language models (LLMs) can learn from a few demonstration examples in a training-free manner, termed ``In-Context Learning" (ICL). Nevertheless, applying LLMs as a text recognizer is unacceptably resource-consuming. Moreover, our pilot experiments on LLMs show that ICL fails in STR, mainly attributed to the insufficient incorporation of contextual information from diverse samples in the training stage. To this end, we introduce E$^2$STR, a STR model trained with context-rich scene text sequences, where the sequences are generated via our proposed in-context training strategy. E$^2$STR demonstrates that a regular-sized model is sufficient to achieve effective ICL capabilities in STR. Extensive experiments show that E$^2$STR exhibits remarkable training-free adaptation in various scenarios and outperforms even the fine-tuned state-of-the-art approaches on public benchmarks.

Live content is unavailable. Log in and register to view live content