paper-with-me

홈 › Papers

An Empirical Study of Scaling Law for OCR

2023-12-29 · Miao Rang, Zhenni Bi, Chuanjian Liu, Yunhe Wang, Kai Han

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 Optical Character Recognition (OCR) have not yet been investigated. To address this, we conducted comprehensive studies that involved examining the correlation 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-ofthe-art on 6 common test benchmarks with a top-1 average accuracy of 97.42%. The models and dataset are publicly available at https://github.com/large-ocr-model/large-ocr-model.github.io.

📄 PDF Abstract BibTeX arXiv:2401.00028

Code (1)

large-ocr-model/large-ocr-model.github.io 공식 구현

Tasks

Optical Character RecognitionOptical Character Recognition (OCR)Scene Text Recognition

Similar Papers 제목 키워드 기반

An Empirical Study of Scaling Laws for Transfer

2024-08-30 · Matthew Barnett

We present a limited empirical study of scaling laws for transfer learning in transformer models. More specifically, we examine a scaling law that incorporates a "transfer gap" term, indicating the effectiveness of pre-t…

Transfer Learning

Understanding Scaling Laws for Recommendation Models

2022-08-17 · Newsha Ardalani, Carole-Jean Wu, Zeliang Chen, Bhargav Bhushanam 외

Scale has been a major driving force in improving machine learning performance, and understanding scaling laws is essential for strategic planning for a sustainable model quality performance growth, long-term resource pl…

Context-Scaling versus Task-Scaling in In-Context Learning

2024-10-16 · Amirhesam Abedsoltan, Adityanarayanan Radhakrishnan, Jingfeng Wu, Mikhail Belkin

Transformers exhibit In-Context Learning (ICL), where these models solve new tasks by using examples in the prompt without additional training. In our work, we identify and analyze two key components of ICL: (1) context-…

In-Context Learning

Limitations of the NTK for Understanding Generalization in Deep Learning

2022-06-20 · Nikhil Vyas, Yamini Bansal, Preetum Nakkiran

The ``Neural Tangent Kernel'' (NTK) (Jacot et al 2018), and its empirical variants have been proposed as a proxy to capture certain behaviors of real neural networks. In this work, we study NTKs through the lens of scali…

Deep Learning

Towards Robust Scaling Laws for Optimizers

2026-02-07 · Alexandra Volkova, Mher Safaryan, Christoph H. Lampert, Dan Alistarh arxiv

The quality of Large Language Model (LLM) pretraining depends on multiple factors, including the compute budget and the choice of optimization algorithm. Empirical scaling laws are widely used to predict loss as model si…