ICML 2017 accepted papers on Image generation
16 of the 435 papers accepted at ICML 2017 (3.7%) are on Image generation, compared with 1.2% at ICML 2016. They fall into 4 topics.
See ICML 2017 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
Autoregressive and latent generation · 8 papers
- Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders (390 citations)
- Toward Controlled Generation of Text (146 citations)
- DeepBach: a Steerable Model for Bach Chorales Generation (125 citations)
- Image-to-Markup Generation with Coarse-to-Fine Attention (87 citations)
- Dual Supervised Learning (72 citations)
- Uncorrelation and Evenness: a New Diversity-Promoting Regularizer (18 citations)
- PixelCNN Models with Auxiliary Variables for Natural Image Modeling (6 citations)
- From Patches to Images: A Nonparametric Generative Model (3 citations)
GANs · 6 papers
- Wasserstein Generative Adversarial Networks (4,925 citations)
- Conditional Image Synthesis with Auxiliary Classifier GANs (2,029 citations)
- Adversarial Feature Matching for Text Generation (243 citations)
- Generalization and Equilibrium in Generative Adversarial Nets (GANs) (199 citations)
- McGan: Mean and Covariance Feature Matching GAN (25 citations)
- Learning Texture Manifolds with the Periodic Spatial GAN (23 citations)
Fast diffusion sampling · 1 paper
- Parallel Multiscale Autoregressive Density Estimation (43 citations)
Image restoration · 1 paper
- Real-Time Adaptive Image Compression (111 citations)
