Augment on Manifold: Mixup Regularization with UMAP
This work addresses the problem of improving generalization in deep learning models for regression tasks, though it appears incremental as it builds on existing Mixup methods.
The paper tackled the limited application of data augmentation beyond computer vision by proposing UMAP Mixup, a regularization scheme that ensures synthesized samples lie on the data manifold, and found it competitive or superior to other Mixup variants in diverse regression tasks.
Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a Mixup regularization scheme, referred to as UMAP Mixup, designed for ``on-manifold" automated data augmentation for deep learning predictive models. The proposed approach ensures that the Mixup operations result in synthesized samples that lie on the data manifold of the features and labels by utilizing a dimensionality reduction technique known as uniform manifold approximation and projection. Evaluations across diverse regression tasks show that UMAP Mixup is competitive with or outperforms other Mixup variants, show promise for its potential as an effective tool for enhancing the generalization performance of deep learning models.