论文标题
元数据增强优化方法
Meta Approach to Data Augmentation Optimization
论文作者
论文摘要
数据增强策略会大大提高图像识别任务的性能，尤其是当对目标数据和任务进行优化策略时。在本文中，我们建议同时优化图像识别模型和数据增强策略，以使用梯度下降来提高性能。与先前的方法不同，我们的方法避免使用代理任务或减少搜索空间，并可以直接改善验证性能。我们的方法通过与Neumann Series近似的隐式梯度近似策略梯度来实现有效且可扩展的训练。我们证明我们的方法可以改善各种图像分类任务的性能，包括ImageNet分类和细粒度识别，而无需使用数据集特定的超参数调整。
Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper, we propose to optimize image recognition models and data augmentation policies simultaneously to improve the performance using gradient descent. Unlike prior methods, our approach avoids using proxy tasks or reducing search space, and can directly improve the validation performance. Our method achieves efficient and scalable training by approximating the gradient of policies by implicit gradient with Neumann series approximation. We demonstrate that our approach can improve the performance of various image classification tasks, including ImageNet classification and fine-grained recognition, without using dataset-specific hyperparameter tuning.
