AIM: an Auto-Augmenter for Images and Meshes

Abstract

Data augmentations are commonly used to increase the robustness of deep neural networks. In most contemporary research, the networks do not decide the augmentations; they are task-agnostic, and grid search determines their magnitudes. Furthermore, augmentations applicable to lower-dimensional data do not easily extend to higher-dimensional data and vice versa. This paper presents an auto-augmenter for images and meshes (AIM) that easily incorporates into neural networks at training and inference times. It Jointly optimizes with the network to produce constrained, non-rigid deformations in the data. AIM predicts sample-aware deformations suited for a task, and our experiments confirm its effectiveness with various networks.