Safe Augmentation: Learning Task-Specific Transformations from Data
This addresses the need for automated, dataset-specific augmentation methods in deep learning, particularly for computer vision, to reduce reliance on expert knowledge and improve model generalization, though it is incremental as it builds on existing augmentation concepts.
The paper tackles the problem of manually designing data augmentation techniques by introducing Safe Augmentation, a method that learns task-specific transformations from data without altering the data distribution, achieving better accuracy on datasets like CIFAR-10, CIFAR-100, SVHN, Tiny ImageNet, and Cityscapes compared to baseline techniques.
Data augmentation is widely used as a part of the training process applied to deep learning models, especially in the computer vision domain. Currently, common data augmentation techniques are designed manually. Therefore they require expert knowledge and time. Moreover, augmentations are dataset-specific, and the optimal augmentations set on a specific dataset has limited transferability to others. We present a simple and explainable method called $\textbf{Safe Augmentation}$ that can learn task-specific data augmentation techniques that do not change the data distribution and improve the generalization of the model. We propose to use safe augmentation in two ways: for model fine-tuning and along with other augmentation techniques. Our method is model-agnostic, easy to implement, and achieves better accuracy on CIFAR-10, CIFAR-100, SVHN, Tiny ImageNet, and Cityscapes datasets comparing to baseline augmentation techniques. The code is available at $\href{https://github.com/Irynei/SafeAugmentation}{https://github.com/Irynei/SafeAugmentation}$.