Scholarlink

Data augmentation is a critical component in building modern deep-learning systems. In this chapter, we propose MFG Augment, a novel data augmentation method based on the Mean-Field-Game (MFG) theory, that can synthesize a sequence of data between every two images or features. The central idea is to consider every image as a distribution over its pixel or feature space. Using Mean-field Game theory, we can generate a time-continuous “path” from one distribution to another so that the points along the “path” are augmented images or features. Empirically, the experiment results on MNIST, CIFAR-10, and ImageNet demonstrate that the proposed technology has better generalization ability and higher classification accuracy as compared to several benchmark methods.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data Augmentation Using Mean Field Games

  • 章节

  • 发表日期：

    2025年

查看全文
  • Yuhan Kang,
  • Hao Gao,
  • Zhu Han

摘要

Data augmentation is a critical component in building modern deep-learning systems. In this chapter, we propose MFG Augment, a novel data augmentation method based on the Mean-Field-Game (MFG) theory, that can synthesize a sequence of data between every two images or features. The central idea is to consider every image as a distribution over its pixel or feature space. Using Mean-field Game theory, we can generate a time-continuous “path” from one distribution to another so that the points along the “path” are augmented images or features. Empirically, the experiment results on MNIST, CIFAR-10, and ImageNet demonstrate that the proposed technology has better generalization ability and higher classification accuracy as compared to several benchmark methods.