Research map / Image generation / GANs
EAGAN: Efficient Two-Stage Evolutionary Architecture Search for GANs
Guohao Ying, Xin He, Bin Gao, Bo Han, Xiaowen Chu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add stage-2 discriminator search after generator search (ablation) | EAGAN · CIFAR-10 | FID: 10.14 -> 9.91 | Improved |
| add stage-2 discriminator search after generator search (ablation) | EAGAN · STL-10 | FID: 23.34 -> 22.18 | Improved |
| add stage-2 discriminator search after generator search (ablation) | EAGAN · STL-10 | IS: 10.02 -> 10.44 | Improved |
| use simple conv initial D in stage-1 instead of the AdversarialNAS discriminator (ablation) | EAGAN · CIFAR-10 | FID: 9.91 -> 12.84 | Mixed |
| repeat two-stage search with previous D as initial D (ablation) | EAGAN · CIFAR-10 | FID: 9.91 -> 10.53 | No clear effect |
| search G first rather than D first (ablation) | EAGAN · CIFAR-10 | gradient stability | Improved |
| decouple G and D search into two stages instead of coupled evolution (ablation) | EAGAN · CIFAR-10 | search stability | Improved |
| add weight-resetting in stage-2 (ablation) | EAGAN · CIFAR-10 | IS and FID during stage-2 | Improved |
| use EAGAN-G instead of AdversarialNAS (G only) | generator search · CIFAR-10 | FID: 24.04 -> 10.14 | Improved |
| use EAGAN-GD1 instead of AlphaGAN when searching G and D | GAN NAS · CIFAR-10 | FID: 15.56 -> 9.91 | Improved |
Closest papers by meaning
- AutoGAN: Neural Architecture Search for Generative Adversarial Networks (ICCV 2019 · similarity 0.93)
- AdversarialNAS: Adversarial Neural Architecture Search for GANs (CVPR 2020 · similarity 0.92)
- AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks (TPAMI 2021 · similarity 0.92)
- Neuroevolution of a Multi-Generator GAN (Student Abstract) (AAAI 2024 · similarity 0.90)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.89)
- The GAN is dead; long live the GAN! A Modern GAN Baseline (NeurIPS 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.
