ICML 2019 accepted papers on Image generation
20 of the 774 papers accepted at ICML 2019 (2.6%) are on Image generation, compared with 2.9% at ICML 2018. They fall into 5 topics.
See ICML 2019 in the interactive map
Submitting to ICML? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
GANs · 14 papers
- Self-Attention Generative Adversarial Networks (2,555 citations)
- High-Fidelity Image Generation With Fewer Labels (124 citations)
- Deep Compressed Sensing (58 citations)
- Lipschitz Generative Adversarial Nets (46 citations)
- Learning Generative Models across Incomparable Spaces (44 citations)
- GDPP: Learning Diverse Generations using Determinantal Point Processes (34 citations)
- HyperGAN: A Generative Model for Diverse, Performant Neural Networks (23 citations)
- CoT: Cooperative Training for Generative Modeling of Discrete Data (21 citations)
- Metropolis-Hastings Generative Adversarial Networks (17 citations)
- Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs (13 citations)
- Adversarial Generation of Time-Frequency Features with application in audio synthesis (12 citations)
- Non-Parametric Priors For Generative Adversarial Networks (7 citations)
and 2 more in the interactive map.
Autoregressive and latent generation · 3 papers
Fast diffusion sampling · 1 paper
- FloWaveNet : A Generative Flow for Raw Audio (28 citations)
Image restoration · 1 paper
- Multi-Frequency Vector Diffusion Maps (1 citation)
Text-to-image diffusion · 1 paper
- Non-Monotonic Sequential Text Generation (62 citations)
