StackMix: A complementary Mix algorithm

John Chen, Samarth Sinha, Anastasios Kyrillidis

Keywords: Data augmentation, Deep Learning

TL;DR: StackMix is an alternative data augmentation technique that supplements the ``Mix'' line of work, and shows favorable performance compared to state of the art.

Abstract: Techniques combining multiple images as input/output have proven to be effective data augmentations for training convolutional neural networks. In this paper, we present StackMix: each input is presented as a concatenation of two images, and the label is the mean of the two one-hot labels. On its own, StackMix rivals other widely used methods in the ``Mix'' line of work. More importantly, unlike previous work, significant gains across a variety of benchmarks are achieved by combining StackMix with existing Mix augmentation, effectively mixing more than two images. E.g., by combining StackMix with CutMix, test error in the supervised setting is improved across a variety of settings over CutMix, including 0.8\% on ImageNet, 3\% on Tiny ImageNet, 2\% on CIFAR-100, 0.5\% on CIFAR-10, and 1.5\% on STL-10. Similar results are achieved with Mixup. We further show that gains hold for robustness to common input corruptions and perturbations at varying severities with a 0.7\% improvement on CIFAR-100-C, by combining StackMix with AugMix over AugMix. On its own, improvements with StackMix hold across different number of labeled samples on CIFAR-100, maintaining approximately a 2\% gap in test accuracy --down to using only 5\% of the whole dataset-- and is effective in the semi-supervised setting with a 2\% improvement with the standard benchmark $\Pi$-model. Finally, we perform an extensive ablation study to better understand the proposed methodology.