Improved Boundary Equilibrium Generative Adversarial Networks

Explore this paper's citation graph

Summary

This work proposes an effective approach to generate images with higher quality and better diversity in BEGANs framework by adding a second loss function (a denoising loss) to the discriminator, so that the ability of discriminator in distinguishing between real and generated images is improved.

Type
article
Published
2018-02-09
Cited by
42
References
27
Access
Open access

Keywords

Discriminator, Normalization (sociology), Computer science, Artificial intelligence, Generator (circuit theory)

References

Cited by

Related papers