LAMBO: Landmarks Augmentation With Manifold-Barycentric Oversampling

LAMBO: Landmarks Augmentation With Manifold-Barycentric Oversampling

We propose the first data augmentation method based on optimal transport theory, with the generated data being guaranteed to belong to the original data manifold. The proposed algorithm randomly samples a clique in the nearest-neighbors graph representing the data knowledge and computes the Wasserst...

Full description

Bibliographic Details
Main Authors: Iaroslav Bespalov, Nazar Buzun, Oleg Kachan, Dmitry V. Dylov
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Augmentation
barycenter
cyclic gererative adversarial networks
landmarks
manifold
optimal transport theory
Online Access:https://ieeexplore.ieee.org/document/9940236/

Internet

https://ieeexplore.ieee.org/document/9940236/

Similar Items