ICML 2018 accepted papers on Image generation
18 of the 623 papers accepted at ICML 2018 (2.9%) are on Image generation, compared with 3.7% at ICML 2017. They fall into 4 topics.
See ICML 2018 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 · 13 papers
- GAIN: Missing Data Imputation using Generative Adversarial Nets (599 citations)
- Optimizing the Latent Space of Generative Networks (196 citations)
- Geometry Score: A Method For Comparing Generative Adversarial Networks (64 citations)
- Is Generator Conditioning Causally Related to GAN Performance? (48 citations)
- Adversarial Learning with Local Coordinate Coding (31 citations)
- Improved Training of Generative Adversarial Networks Using Representative Features (28 citations)
- Mixed batches and symmetric discriminators for GAN training (23 citations)
- Chi-square Generative Adversarial Network (12 citations)
- Composite Functional Gradient Learning of Generative Adversarial Models (11 citations)
- First Order Generative Adversarial Networks (6 citations)
- Learning Implicit Generative Models with the Method of Learned Moments (6 citations)
- Tempered Adversarial Networks (2 citations)
and 1 more in the interactive map.
Fast diffusion sampling · 2 papers
- Parallel WaveNet: Fast High-Fidelity Speech Synthesis (335 citations)
- Autoregressive Quantile Networks for Generative Modeling (31 citations)
Image restoration · 2 papers
Super-resolution · 1 paper
- Image Transformer (227 citations)
