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; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 15567-15576

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 E2STR a STR model trained with context-rich scene text sequences where the sequences are generated via our proposed in-context training strategy. E2STR demonstrates that a regular-sized model is sufficient to achieve effective ICL capabilities in STR. Extensive experiments show that E2STR exhibits remarkable training-free adaptation in various scenarios and outperforms even the fine-tuned state-of-the-art approaches on public benchmarks. The code is released at https://github.com/bytedance/E2STR.