ICML 2020 accepted papers on Image generation
17 of the 1,087 papers accepted at ICML 2020 (1.6%) are on Image generation, compared with 2.6% at ICML 2019. They fall into 3 topics.
See ICML 2020 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 · 9 papers
- Leveraging Frequency Analysis for Deep Fake Image Recognition (206 citations)
- AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks (64 citations)
- On Leveraging Pretrained GANs for Generation with Limited Data (55 citations)
- Small-GAN: Speeding up GAN Training using Core-Sets (38 citations)
- Understanding and Stabilizing GANs’ Training Dynamics Using Control Theory (10 citations)
- Learning disconnected manifolds: a no GAN’s land (9 citations)
- Multilinear Latent Conditioning for Generating Unseen Attribute Combinations (8 citations)
- T-GD: Transferable GAN-generated Images Detection Framework (6 citations)
- Bridging the Gap Between f-GANs and Wasserstein GANs
Autoregressive and latent generation · 7 papers
- Reliable Fidelity and Diversity Metrics for Generative Models (54 citations)
- ControlVAE: Controllable Variational Autoencoder (49 citations)
- Educating Text Autoencoders: Latent Representation Guidance via Denoising (30 citations)
- A Tree-Structured Decoder for Image-to-Markup Generation (26 citations)
- Latent Space Factorisation and Manipulation via Matrix Subspace Projection (14 citations)
- On the Relation between Quality-Diversity Evaluation and Distribution-Fitting Goal in Text Generation (4 citations)
- Adversarial Mutual Information for Text Generation
