Research map / Image generation / GANs
Robust Conditional 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 |
|---|---|---|---|
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Faces, denoising 25% | SSIM: 0.803 -> 0.834 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Faces, denoising 35% | SSIM: 0.765 -> 0.821 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Faces, sparse inpainting 50% | SSIM: 0.801 -> 0.804 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Faces, sparse inpainting 75% | SSIM: 0.701 -> 0.708 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Natural scenes, denoising 25% | SSIM: 0.628 -> 0.668 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Natural scenes, denoising 35% | SSIM: 0.599 -> 0.654 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Natural scenes, sparse inpainting 50% | SSIM: 0.639 -> 0.648 | Helped |
| Replace the single-path cGAN generator with RoCGAN's target-domain autoencoder pathway and shared decoder | cGAN · Natural scenes, sparse inpainting 75% | SSIM: 0.542 -> 0.548 | Helped |
| Use the two-pathway generator instead of a single-path generator | synthetic regression network · Synthetic data | L1 error: 9,843 -> 1,520 | Helped |
| Train the target-domain autoencoder pathway with additional unlabelled target images | RoCGAN-4layer-50k · Faces, semi-supervised denoising 25% | SSIM: 0.788 -> 0.829 | Helped |
Closest papers by meaning
- Robustness of conditional GANs to noisy labels (NeurIPS 2018 · similarity 0.93)
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (ICLR 2021 · similarity 0.93)
- Diversity-Sensitive Conditional Generative Adversarial Networks (ICLR 2019 · similarity 0.93)
- Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks (AAAI 2024 · similarity 0.89)
- Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation (AAAI 2024 · similarity 0.88)
- Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions (CVPR 2024 · 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.