An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator
2021
Generative Adversarial Networks (GANs) have emerged as useful generative
models, which are capable of implicitly learning data distributions of
arbitrarily complex dimensions. However, the training of GANs is empirically
well-known for being highly unstable and sensitive. The loss functions of both
the discriminator and generator concerning their parameters tend to oscillate
wildly during training. Different loss functions have been proposed to
stabilize the training and improve the quality of images generated. In this
paper, we perform an empirical study on the impact of several loss functions on
the performance of standard GAN models, Deep Convolutional Generative
Adversarial Networks (DCGANs). We introduce a new improvement that employs a
relativistic discriminator to replace the classical deterministic discriminator
in DCGANs and implement a margin cosine loss function for both the generator
and discriminator. This results in a novel loss function, namely
\textit{Relativistic Margin Cosine Loss} (RMCosGAN). We carry out extensive
experiments with four datasets: CIFAR-$10$, MNIST, STL-$10$, and CAT. We
compare RMCosGAN performance with existing loss functions based on two metrics:
Frechet inception distance and inception score. The experimental results show
that RMCosGAN outperforms the existing ones and significantly improves the
quality of images generated.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
23
References
0
Citations
NaN
KQI