Landmarks Augmentation with Manifold-Barycentric Oversampling
This addresses data scarcity in machine learning, particularly for landmarks detection and medical segmentation, but appears incremental as it builds on existing augmentation and optimal transport techniques.
The paper tackles the problem of limited training data for Generative Adversarial Networks (GANs) by proposing a new augmentation method that uses optimal transport theory to generate new data within the original manifold, resulting in reduced overfitting and improved quality metrics beyond original data and modern augmentation methods.
The training of Generative Adversarial Networks (GANs) requires a large amount of data, stimulating the development of new augmentation methods to alleviate the challenge. Oftentimes, these methods either fail to produce enough new data or expand the dataset beyond the original manifold. In this paper, we propose a new augmentation method that guarantees to keep the new data within the original data manifold thanks to the optimal transport theory. The proposed algorithm 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 annotation in both unpaired and in semi-supervised scenarios. Additionally, the idea is validated on cardiac data for the task of medical segmentation. Our approach reduces the overfitting and improves the quality metrics beyond the original data outcome and beyond the result obtained with popular modern augmentation methods.