Research map / Architectures and efficiency / Neural architecture search
AdversarialNAS: Adversarial Neural Architecture Search for GANs
Chen Gao, Yunpeng Chen, Si Liu, Zhenxiong Tan, Shuicheng Yan
Check 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 |
|---|---|---|---|
| search generator and discriminator architectures dynamically in an adversarial competition instead of searching the generator against a fixed discriminator (ablation) | AdversarialNAS · CIFAR-10 | FID: 23.01 -> 10.87 | Improved |
| search generator and discriminator architectures dynamically in an adversarial competition instead of searching the generator against a fixed discriminator (ablation) | AdversarialNAS · STL-10 | FID: 41.57 -> 26.98 | Improved |
| replace random search with differentiable adversarial architecture search (ablation) | AdversarialNAS · CIFAR-10 | FID: 38.32 -> 10.87 | Improved |
| replace random search with differentiable adversarial architecture search (ablation) | AdversarialNAS · STL-10 | FID: 53.45 -> 26.98 | Improved |
| transfer the CIFAR-10-searched generator to STL-10 and retrain its weights | AdversarialNAS-GAN · STL-10 | FID | Improved |
| use fixed SNGAN-D instead of dynamically searching the discriminator (ablation) | AdversarialNAS · CIFAR-10 | IS: 8.74±0.07 -> 7.72±0.03 | Hurt |
| use fixed AutoGAN-D instead of dynamically searching the discriminator (ablation) | AdversarialNAS · CIFAR-10 | IS: 8.74±0.07 -> 7.86±0.08 | Hurt |
| use fixed AutoGAN-D instead of dynamically searching the discriminator (ablation) | AdversarialNAS · STL-10 | FID: 38.85 -> 26.98 | Hurt |
| use fixed Super-D instead of dynamically searching the discriminator (ablation) | AdversarialNAS · STL-10 | IS: 9.63±0.19 -> 8.62±0.03 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AutoGAN — AutoGAN: Neural Architecture Search for Generative Adversarial Networks (ICCV 2019) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- AutoGAN: Neural Architecture Search for Generative Adversarial Networks (ICCV 2019 · similarity 0.92)
- EAGAN: Efficient Two-Stage Evolutionary Architecture Search for GANs (ECCV 2022 · similarity 0.92)
- AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks (TPAMI 2021 · similarity 0.91)
- Robust NAS under adversarial training: benchmark, theory, and beyond (ICLR 2024 · similarity 0.89)
- Towards Accurate and Robust Architectures via Neural Architecture Search (CVPR 2024 · similarity 0.87)
- Towards Neural Architecture Search through Hierarchical Generative Modeling (ICML 2024 · similarity 0.87)
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.
