Augment on Manifold: Mixup Regularization with UMAP
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDeep LearningDimensionality ReductionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Simplicial Regularization
Inspired by the fuzzy topological representation of a dataset employed in UMAP (McInnes et al., 2018), we propose a regularization principle for supervised learning based on the preservation of the simplicial complex str…
Data AugmentationDimensionality ReductionMixUp as Locally Linear Out-Of-Manifold Regularization
MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with su…
Data AugmentationNoisy Feature Mixup
We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes. Rather than training with convex combi…
Data AugmentationPreventing Manifold Intrusion with Locality: Local Mixup
Mixup is a data-dependent regularization technique that consists in linearly interpolating input samples and associated outputs. It has been shown to improve accuracy when used to train on standard machine learning datas…
Image ClassificationMulti-Sample $ζ$-mixup: Richer, More Realistic Synthetic Samples from a $p$-Series Interpolant
Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information. A…
Data AugmentationDiversityimage-classificationImage Classification+1