AutoGAN applies reinforcement-learning-based neural architecture search to GAN generators, discovering a CIFAR-10 architecture with FID 12.42 and an STL-10 FID 31.01, both state of the art in 2019.
Searching for efficient multi-scale archi- tectures for dense image prediction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AutoGAN: Neural Architecture Search for Generative Adversarial Networks
AutoGAN applies reinforcement-learning-based neural architecture search to GAN generators, discovering a CIFAR-10 architecture with FID 12.42 and an STL-10 FID 31.01, both state of the art in 2019.