AI 中文总结
GERIS提出博弈论框架，通过非合作博弈筛选车牌数据增强中的低质量噪声实例，提升分类准确性和鲁棒性。
AI 中文摘要
在本文中，我们提出了GERIS，一种用于车牌识别系统数据增强阶段实例选择的博弈论框架。在增强过程中，合成车牌图像通过随机噪声进行生成和变换，以模拟真实世界条件。然而，某些噪声配置会导致高度失真、不可读的图像，这些图像通过引入实例相关的标签噪声而降低模型性能。GERIS构建了一个非合作博弈，其中每个噪声向量根据其与标记数据的相似性及其对模型可靠性的贡献，竞争纳入训练集。通过识别和修剪低质量实例，GERIS提高了增强数据集的整体质量。与传统的黑盒学习方法不同，GERIS提供了一种透明、有理论依据的数据过滤机制。实验结果表明，GERIS在分类准确性和鲁棒性方面优于现有的实例选择方法。
英文摘要
In this paper, we propose GERIS, a game-theoretic framework for instance selection in the data augmentation phase of license plate recognition systems. During augmentation, synthetic license plate images are generated and transformed using stochastic noise to simulate real-world conditions. However, certain noise configurations lead to highly distorted, unreadable images that degrade model performance by introducing instance-dependent label noise. GERIS formulates a non-cooperative game in which each noise vector competes for inclusion in the training set based on its similarity to labeled data and its contribution to model reliability. By identifying and pruning low-quality instances, GERIS improves the overall quality of the augmented dataset. Unlike traditional black-box learning methods, GERIS offers a transparent, theoretically grounded mechanism for data filtering. Experimental results demonstrate that GERIS outperforms existing instance selection methods in terms of classification accuracy and robustness.
Comments23 pages, 4 figures. To appear in AUT Journal of Mathematics and Computing (AUT J Math Comput)
DOI：10.22060/ajmc.2025.23680.1288
