TechRxiv
sqp.pdf (437.14 kB)

SequenceGan: Text to Image Synthesis with Sequence Models and Gans

Download (437.14 kB)
preprint
posted on 02.08.2021, 22:04 by Yigit GunducYigit Gunduc
Generative Adversarial Nets are one of the most popular generative frameworks. In our work, we introduce the SequenceGAN, a method that can generate images based on a given caption by supplying the conditional sequential text input to the generator and the discriminator. Unlike other conditional methods, SequenceGAN uses recurrent layers for better context understanding. We also demonstrated SequenceGANs performance by applying it to the MNIST and Flickr 8k datasets.

History

Email Address of Submitting Author

ygunduc@gmail.com

ORCID of Submitting Author

https://orcid.org/0000-0001-5210-4088

Submitting Author's Institution

Ankara University Development Foundation Private High School

Submitting Author's Country

Turkey

Usage metrics

Licence

Exports