Meta Approach to Data Augmentation Optimization

Meta Approach to Data Augmentation Optimization
复制标题

DOI:
10.1109/wacv51458.2022.00359
复制
发表时间:
2020-06
期刊:
2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
影响因子:
--
通讯作者:
Ryuichiro Hataya;Jan Zdenek;Kazuki Yoshizoe;Hideki Nakayama
Ryuichiro Hataya;Jan Zdenek;Kazuki Yoshizoe;Hideki Nakayama
中科院分区:
其他
文献类型:
--
作者:
Ryuichiro Hataya;Jan Zdenek;Kazuki Yoshizoe;Hideki Nakayama

文献摘要

相似文献

数据增强策略极大地提高了图像识别任务的性能,特别是当策略针对目标数据和任务进行优化时。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。与之前的方法不同,我们的方法避免使用代理任务或减少搜索空间,并且可以直接提高验证性能。我们的方法通过诺伊曼级数近似的隐式梯度来近似策略的梯度,实现了高效且可扩展的训练。我们证明,我们的方法可以提高各种图像分类任务的性能,包括细粒度图像识别,而无需使用特定于数据集的超参数调整。
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 fine-grained image recognition, without using dataset-specific hyperparameter tuning.