An Empirical Study of Scaling Law for Scene Text Recognition

Miao Rang, Zhenni Bi, Chuanjian Liu, Yunhe Wang, Kai Han; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 15619-15629

Abstract


The laws of model size data volume computation and model performance have been extensively studied in the field of Natural Language Processing (NLP). However the scaling laws in Scene Text Recognition (STR) have not yet been investigated. To address this we conducted comprehensive studies that involved examining the correlations between performance and the scale of models data volume and computation in the field of text recognition. Conclusively the study demonstrates smooth power laws between performance and model size as well as training data volume when other influencing factors are held constant. Additionally we have constructed a large-scale dataset called REBU-Syn which comprises 6 million real samples and 18 million synthetic samples. Based on our scaling law and new dataset we have successfully trained a scene text recognition model achieving a new state-of-the-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%. The models and dataset are publicly available at \href https://github.com/large-ocr-model/large-ocr-model.github.io large-ocr-model.github.io .

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Rang_2024_CVPR, author = {Rang, Miao and Bi, Zhenni and Liu, Chuanjian and Wang, Yunhe and Han, Kai}, title = {An Empirical Study of Scaling Law for Scene Text Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {15619-15629} }