Self-Attention Generative Adversarial Networks

Explore this paper's citation graph

Summary

The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.

Type
preprint
Published
2018-05-21
Cited by
4,180
References
54
Access
Open access

Keywords

Discriminator, Boosting (machine learning), Computer science, Normalization (sociology), Generative grammar

References

Cited by

Related papers