AutoAugment是一种使用强化学习自动寻找数据增强策略的方法，旨在提高模型对数据不变性的理解。通过控制器RNN预测增强策略，训练固定架构的子网络，并基于验证准确性反馈进行更新。搜索空间包括不同图像处理操作及其概率和幅度。尽管有效，但该方法可能增加训练复杂性和计算成本，且难以适应不同模型和数据集的需求。
AutoAug
背景：
Data augmentation is a effective technique to increase both the amount and diversity of data by randomly “augmenting” it.
直觉上讲，数据增强教会了模型数据不变性
目标：
we aim to automate the process of finding an effective data augmentation policy for a target dataset.
use Reinforcement Learning as the search algorithm
优点：
-
AutoAugment can be applied directly on the dataset of interest to find the best augmentation policy (AutoAugment-direct)
-
learned policies can be transferred to new datasets (AutoAugment-transfer). that policies found on one task can generalize well across different models and datasets.
- each operation being an image processing function such as translation, rotation, or shearing and the probabilities and magnitudes
- search algorithm to find
最低0.47元/天 解锁文章
540
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
