Robust and Generalizable Visual Representation Learning via Random Convolutions
RandConv: 通过随机卷积实现鲁棒和泛化的视觉表示学习.
使用torchvision.transforms进行图像增强
Image Augmentation with torchvision.transforms.
TrivialAugment: Tuning-free Yet State-of-the-Art Data Augmentation
TrivialAugment: 无需调优的先进数据增强.
RandAugment: Practical automated data augmentation with a reduced search space
RandAugment: 通过减少搜索空间实现自动数据增强.
AutoAugment: Learning Augmentation Policies from Data
AutoAugment: 从数据中学习增强策略.
Random Erasing Data Augmentation
随机擦除数据增强.