MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning

TL;DR

MetaMixUp introduces a meta-learning approach to adaptively learn interpolation policies for MixUp, improving data augmentation effectiveness and boosting performance in supervised and semi-supervised learning tasks.

Contribution

The paper proposes MetaMixUp, a novel meta-learning based method to dynamically learn interpolation policies, addressing limitations of random MixUp sampling.

Findings

MetaMixUp outperforms vanilla MixUp and variants in supervised learning.

MetaMixUp significantly improves semi-supervised learning results on CIFAR-10 and SVHN.

The adaptive interpolation policy enhances model regularization and generalization.

Abstract

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and domain adaption. However, despite its empirical success, its deficiency of randomly mixing samples has poorly been studied. Since deep networks are capable of memorizing the entire dataset, the corrupted samples generated by vanilla MixUp with a badly chosen interpolation policy will degrade the performance of networks. To overcome the underfitting by corrupted samples, inspired by Meta-learning (learning to learn), we propose a novel technique of learning to mixup in this work, namely, MetaMixUp. Unlike the vanilla MixUp that samples interpolation policy from a predefined distribution, this paper introduces a meta-learning based online optimization approach to dynamically learn the interpolation policy in a data-adaptive way. The validation set performance via meta-learning captures the underfitting issue, which provides more information to refine interpolation policy. Furthermore, we adapt our method for pseudo-label based semisupervised learning (SSL) along with a refined pseudo-labeling strategy. In our experiments, our method achieves better performance than vanilla MixUp and its variants under supervised learning configuration. In particular, extensive experiments show that our MetaMixUp adapted SSL greatly outperforms MixUp and many state-of-the-art methods on CIFAR-10 and SVHN benchmarks under SSL configuration.