Multi-objective training of Generative Adversarial Networks with multiple discriminators

By Isabela Albuquerque, João Monteiro, Thang Van Doan, Breandan Considine, Tiago H. Falk, Ioannis Mitliagkas. 2019

72 citations recorded by the source corpus.

Recent literature has demonstrated promising results for training Generative Adversarial Networks by employing a set of discriminators, in contrast to the traditional game involving one generator against a single adversary. Such methods perform single-objective optimization on some simple consolidation of the losses, e.g. an arithmetic average. In this work, we revisit the multiple-discriminator setting by framing the simultaneous minimization of losses provided by different models as a multi-objective optimization problem. Specifically, we evaluate the performance of multiple gradient descent and the hypervolume maximization algorithm on a number of different datasets. Moreover, we argue that the previously proposed methods and hypervolume maximization can all be seen as variations of multiple gradient descent in which the update direction can be computed efficiently. Our results indicate that hypervolume maximization presents a better compromise between sample quality and computational cost than previous methods.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Ngai-Man Cheung
3. Ngoc-Trung Tran
4. Viet-Hung Tran
5. Ngoc-Bao Nguyen
6. Ioannis Mitliagkas
7. Axel Sauer
8. Trung-Kien Nguyen

In Computational Mechanics

1. Dacheng Tao
2. Jie Gui
3. Jieping Ye
4. Divya Saxena
5. Jiannong Cao
6. Yonggang Wen
7. Zhenan Sun
8. Ioannis Mitliagkas

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Andreas Geiger
3. Luc Van Gool
4. Zhenan Sun
5. Ngai-Man Cheung
6. Viet-Hung Tran
7. Ngoc-Trung Tran
8. Ngoc-Bao Nguyen

In Generative Models

1. Axel Sauer
2. Andreas Geiger
3. Ioannis Mitliagkas
4. Ngai-Man Cheung
5. Ngoc-Trung Tran
6. Viet-Hung Tran
7. Ngoc-Bao Nguyen
8. Divya Saxena

Citations in the corpus

• Projected GANs Converge Faster (2021, background): “A different line of work considers a setup with multiple discriminators, applied to either the generated RGB image [8, 13] or low-dimensional projections thereof [1, 40].”
• Multi-Task Self-Supervised Learning for Robust Speech Recognition (2020, neutral): “We conducted experiments to add dynamic weights to each worker, exploring, for instance, the use of the hypervolume maximization [28].”
• Generative Adversarial Networks (GANs) (2020, background): “Reference [130] extended this single-objective optimization problem to multi-objective in which losses provided by different models are minimized simultaneously.”
• Adversarial target-invariant representation learning for domain generalization (2019, background): “Namely, a random projection layer is introduced to the input of each domain discriminator, as in (Neyshabur et al., 2017; Albuquerque et al., 2019).”
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “[211] performed multi-objective training of GANs with multiple discriminators.”
• On Data Augmentation for GAN Training (2020, methodology): “Instead of using only one discriminator or generator like standard GAN, the mixture models are proposed, such as multiple discriminators [39], [40], [41], the mixture of generators [42], [43] or an attacker applied as a new player for GAN training [44].”