DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning. (arXiv:2311.01295v1 [cs.LG])

Data augmentation techniques, such as simple image transformations and
combinations, are highly effective at improving the generalization of computer
vision models, especially when training data is limited. However, such
techniques are fundamentally incompatible with differentially private learning
approaches, due to the latter's built-in assumption that each training image's
contribution to the learned model is bounded. In this paper, we investigate why
naive applications of multi-sample data augmentation techniques, such as mixup,
fail to achieve good performance and propose two novel …

augmentation computer computer vision data image private simple techniques training training data