# Maximum Entropy Regularization and Chinese Text Recognition

arXiv: https://arxiv.org/abs/2007.04651 · HTML: https://mlsanity.com/paper/2007.04651/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2020.

## Built on by (most cited first, 4 of 4)

- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [LISTER: Neighbor Decoding for Length-Insensitive Scene Text Recognition](https://mlsanity.com/paper/2308.12774/) (2023)
- [SAN: Structure-Aware Network for Complex and Long-tailed Chinese Text Recognition](https://mlsanity.com/paper/2411.06381/) (2024)
- [Can Scene Text Recognition Read Rare Compositions?](https://mlsanity.com/paper/2609.00816/) (2026)

## Abstract (arXiv)

Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem. We propose to apply Maximum Entropy Regularization to regularize the training process, which is to simply add a negative entropy term to the canonical cross-entropy loss without any additional parameters and modification of a model. We theoretically give the convergence probability distribution and analyze how the regularization influence the learning process. Experiments on Chinese character recognition, Chinese text line recognition and fine-grained image classification achieve consistent improvement, proving that the regularization is beneficial to generalization and robustness of a recognition model.