Manifold Adversarial Training

Manifold Adversarial Training (MAT) is a novel method to smooth the distributional manifold in the latent space.

Data and Resources

Cite this as

Shufei Zhang, Kaizhu Huang, Jianke Zhu, Yang Liu (2024). Dataset: Manifold Adversarial Training. https://doi.org/10.57702/fr4lhjpp

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.1807.05832
Author Shufei Zhang
More Authors
Kaizhu Huang
Jianke Zhu
Yang Liu