Research map / Image generation / GANs
Mining GOLD Samples for Conditional GANs
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 |
|---|---|---|---|
| Re-weight generated-sample training losses using GOLD | ACGAN · SVHN | fitting capacity (%): 74.43 -> 76.71 (+3.06%) | Helped |
| Use GOLD-based rejection sampling | ACGAN · SVHN | fitting capacity (%): 73.58 to 75.06 (+2.01%) | Helped |
| Use GOLD-based active learning queries instead of random queries | InfoGAN · MNIST | fitting capacity: 92.65 -> 94.60 | Helped |
| Set the rejection sampling parameter to p = 0.1 instead of p = 0.5 (ablation) | GOLD rejection sampling · CIFAR-10 | fitting capacity (%): 35.98 $\pm$1.15 -> 35.80 $\pm$0.42 | Hurt |
| Set the rejection sampling parameter to p = 0.3 instead of p = 0.5 (ablation) | GOLD rejection sampling · CIFAR-10 | fitting capacity (%): 35.98 $\pm$1.15 -> 35.87 $\pm$0.61 | No clear effect |
| Set the rejection sampling parameter to p = 0.7 instead of p = 0.5 (ablation) | GOLD rejection sampling · CIFAR-10 | fitting capacity (%): 35.98 $\pm$1.15 -> 35.85 $\pm$0.53 | No clear effect |
| Set the rejection sampling parameter to p = 0.9 instead of p = 0.5 (ablation) | GOLD rejection sampling · CIFAR-10 | fitting capacity (%): 35.98 $\pm$1.15 -> 35.33 $\pm$0.53 | Hurt |
| Use a smaller auxiliary-classifier loss weight, such as lambda_c = 0.1, rather than the original value of 1 (ablation) | ACGAN · various datasets | fitting capacity | Helped |
| Keep the generator and re-initialize the discriminator between active-learning rounds (ablation) | GOLD active learning · active-learning experiments | fitting capacity | Helped |
Closest papers by meaning
- A Unified View of cGANs with and without Classifiers (NeurIPS 2021 · similarity 0.90)
- Robust Conditional Generative Adversarial Networks (ICLR 2019 · similarity 0.89)
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (ICLR 2021 · similarity 0.88)
- Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training (NeurIPS 2021 · similarity 0.88)
- Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks (AAAI 2024 · similarity 0.86)
- Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions (CVPR 2024 · similarity 0.86)
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.