Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data augmentation strategy called "Universal Adaptive Data Augmentation" (UADA). Different from existing methods, UADA would adaptively update DA's parameters according to the target model's gradient information during training: given a pre-defined set of DA operations, we randomly decide types and magnitudes of DA operations for every data batch during training, and adaptively update DA's parameters along the gradient direction of the loss concerning DA's parameters. In this way, UADA can increase the training loss of the target networks, and the target networks would learn features from harder samples to improve the generalization. Moreover, UADA is very general and can be utilized in numerous tasks, e.g., image classification, semantic segmentation and object detection. Extensive experiments with various models are conducted on CIFAR-10, CIFAR-100, ImageNet, tiny-ImageNet, Cityscapes, and VOC07+12 to prove the significant performance improvements brought by UADA.

翻译：现有自动数据增强方法要么忽略训练过程中根据目标模型状态更新数据增强参数，要么采用的更新策略效果不足。本文设计了一种名为"通用自适应数据增强"（UADA）的新型数据增强策略。与现有方法不同，UADA能够在训练过程中根据目标模型的梯度信息自适应更新数据增强参数：给定预定义的数据增强操作集合，我们在训练期间对每个数据批次随机决定数据增强操作的类型和幅度，并沿关于数据增强参数的损失梯度方向自适应更新这些参数。通过这种方式，UADA能够提升目标网络的训练损失，使目标网络从更难样本中学习特征以增强泛化能力。此外，UADA具有高度通用性，可应用于图像分类、语义分割和目标检测等众多任务。我们在CIFAR-10、CIFAR-100、ImageNet、tiny-ImageNet、Cityscapes和VOC07+12数据集上使用多种模型进行了大量实验，证明了UADA带来的显著性能提升。