A classification-based study of covariate shift in GAN distributions
© 35th International Conference on Machine Learning, ICML 2018.All Rights Reserved. A basic, and still largely unanswered, question in the context of Generative Adversarial Networks (GANs) is whether they are truly able to capture all the fundamental characteristics of the distributions they are tra...
Main Authors: | Madry, Aleksander (Author), Schmidt, Ludwig (Author), Santurkar, Shibani (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
2022-04-14T19:44:47Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
A classification-based study of covariate shift in GAN distributions
by: Madry, Aleksander, et al.
Published: (2021) -
Adversarially Robust Generalization Requires More Data
by: Schmidt, Ludwig, et al.
Published: (2021) -
Leveraging Sparse Linear Layers for Debuggable Deep Networks
by: Wong, Eric, et al.
Published: (2022) -
How does batch normalization help optimization?
by: Madry, Aleksander, et al.
Published: (2021) -
On the limitations of first-order approximation in GAN dynamics
by: Madry, Aleksander
Published: (2021)