Log In Sign Up

Data Augmentation with Manifold Barycenters

by   Iaroslav Bespalov, et al.

The training of Generative Adversarial Networks (GANs) requires a large amount of data, stimulating the development of new data augmentation methods to alleviate the challenge. Oftentimes, these methods either fail to produce enough new data or expand the dataset beyond the original knowledge domain. In this paper, we propose a new way of representing the available knowledge in the manifold of data barycenters. Such a representation allows performing data augmentation based on interpolation between the nearest data elements using Wasserstein distance. The proposed method finds cliques in the nearest-neighbors graph and, at each sampling iteration, randomly draws one clique to compute the Wasserstein barycenter with random uniform weights. These barycenters then become the new natural-looking elements that one could add to the dataset. We apply this approach to the problem of landmarks detection and augment the available landmarks data within the dataset. Additionally, the idea is validated on cardiac data for the task of medical segmentation. Our approach reduces the overfitting and improves the quality metrics both beyond the original data outcome and beyond the result obtained with classical augmentation methods.


page 1

page 2

page 3

page 4

page 5

page 8

page 9

page 10


SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness

Models that perform well on a training domain often fail to generalize t...

Learning Data Augmentation for Brain Tumor Segmentation with Coarse-to-Fine Generative Adversarial Networks

There is a common belief that the successful training of deep neural net...

Data Augmentation Using Adversarial Training for Construction-Equipment Classification

Deep learning-based construction-site image analysis has recently made g...

Augmentation Invariant Manifold Learning

Data augmentation is a widely used technique and an essential ingredient...

MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining

Deep Generative Networks (DGNs) are extensively employed in Generative A...

Are you wearing a mask? Improving mask detection from speech using augmentation by cycle-consistent GANs

The task of detecting whether a person wears a face mask from speech is ...

Normal-bundle Bootstrap

Probabilistic models of data sets often exhibit salient geometric struct...