Research map / Image generation / GANs
Collaborative Sampling in Generative Adversarial Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use discriminator gradients to refine generated samples | GAN sampling · Imbalanced 8-Gaussian mixture | sample quality and diversity | Helped |
| Add discriminator shaping using refined samples (ablation) | Collaborative sampling on NS-GAN · MNIST | classifier score and Fréchet distance | Helped |
| Remove discriminator shaping (ablation) | Collaborative sampling on NS-GAN · MNIST | image quality | Hurt |
| Refine at a middle generator layer instead of the output or input layer (ablation) | Collaborative sampling on NS-GAN · MNIST | refinement balance | Helped |
| Vary the refinement layer from output to low-level activation (ablation) | Collaborative sampling · MNIST | scope of sample modifications | Mixed |
| Use Brier Score rather than Z-statistic or ECE to diagnose the discriminator | Rejection sampling after refinement · Imbalanced 8-Gaussian mixture | correlation with performance gain from rejection | Helped |
| Apply collaborative refinement instead of standard GAN sampling | DCGAN and SAGAN · CIFAR10, CelebA, and ImageNet | IS and FID | Helped |
| Apply collaborative refinement to translated images | CycleGAN · Horse-to-zebra image translation | image quality | Helped |
Closest papers by meaning
- On-Line Adaptative Curriculum Learning for GANs (AAAI 2019 · similarity 0.91)
- Mixed batches and symmetric discriminators for GAN training (ICML 2018 · similarity 0.90)
- MGAN: Training Generative Adversarial Nets with Multiple Generators (ICLR 2018 · similarity 0.90)
- Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling (CVPR 2025 · similarity 0.89)
- Consistency-GAN: Training GANs with Consistency Model (AAAI 2024 · similarity 0.89)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.