# Maximum Entropy Regularization and Chinese Text Recognition

Source: [Maximum Entropy Regularization and Chinese Text Recognition](<https://www.sota2.com/research/paper/68fa67e31e209131cea18e53>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:24:01.852Z

Authors: Changxu Cheng, Wuheng Xu, Xiang Bai, Bin Feng, Wenyu Liu

Published: 2020-07-09T09:19:56.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.04651>)

[PDF](<https://arxiv.org/pdf/2007.04651.pdf>)