ru
ru
Source
ICML
DATE OF PUBLICATION
07/13/2022
Authors
Arip Asadulaev Rostislav Korst
Share

Adversarial Training Improves Joint Energy-Based Generative Modelling

Adversarial training, Energy-based models

Abstract

We propose the novel framework for generative modelling using hybrid energy-based models. In our method we combine the interpretable input gradients of the robust classifier and Langevin Dynamics for sampling. Using the adversarial training we improve not only the training stability, but robustness and generative modelling of the joint energy-based models.

Full text

Similar publications

NeurIPS
Kantorovich Strikes Back! Wasserstein GANs are not Optimal Transport?
Evgeny Burnaev, Alexander Korotin, Alexander Kolesov
SOURCE
CVPR
Sphere-Guided Training of Neural Implicit Surfaces
Andreea Dogaru, Andrei-Timotei Ardelean, Savva Ignatyev, Egor Zakharov, Evgeny Burnaev
SOURCE
ICLR
Learning topology-preserving data representations
Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii, Nikita Balabin, Evgeny Burnaev, Serguei Barannikov
SOURCE
CVPR
Multi-sensor large-scale dataset for multi-view 3D reconstruction
Oleg Voynov , Gleb Bobrovskikh, Pavel Karpyshev, Saveliy Galochkin, Andrei-Timotei Ardelean, Arseniy Bozhenko, Ekaterina Karmanova, Pavel Kopanev, Yaroslav Labutin-Rymsho, Ruslan Rakhimov, Aleksandr Safin, Valerii Serpiva, Alexey Artemov, Evgeny Burnaev, Dzmitry Tsetserukou, Denis Zorin
SOURCE
IEEE Access
Multi-neus: 3d head portraits from single image with neural implicit functions
Egor Burkov, Ruslan Rakhimov, Aleksandr Safin, Evgeny Burnaev, Victor Lempitsky
SOURCE
Sustainability
Practical AI Cases for Solving ESG Challenges
Evgeny Burnaev, Evgeny Mironov, Aleksei Shpilman, Maxim Mironenko, Dmitry Katalevsky
SOURCE
IEEE Access
Pseudo-Labeling Approach for Land Cover Classification Through Remote Sensing Observations With Noisy Labels
Islombek Mirpulatov, Svetlana Illarionova, Dmitrii Shadrin, Evgeny Burnaev
SOURCE
Contact us
Join AIRI
You can ask us a question or suggest a joint project in the field of AI

Message sent.

Thank you!

Something went wrong. Try again