AI Paper Atlas

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

CVPR 2020 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 111 citations (OpenAlex)

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 changedWhereMeasuredEffect
search generator and discriminator architectures dynamically in an adversarial competition instead of searching the generator against a fixed discriminator (ablation)AdversarialNAS · CIFAR-10FID: 23.01 -> 10.87Improved
search generator and discriminator architectures dynamically in an adversarial competition instead of searching the generator against a fixed discriminator (ablation)AdversarialNAS · STL-10FID: 41.57 -> 26.98Improved
replace random search with differentiable adversarial architecture search (ablation)AdversarialNAS · CIFAR-10FID: 38.32 -> 10.87Improved
replace random search with differentiable adversarial architecture search (ablation)AdversarialNAS · STL-10FID: 53.45 -> 26.98Improved
transfer the CIFAR-10-searched generator to STL-10 and retrain its weightsAdversarialNAS-GAN · STL-10FIDImproved
use fixed SNGAN-D instead of dynamically searching the discriminator (ablation)AdversarialNAS · CIFAR-10IS: 8.74±0.07 -> 7.72±0.03Hurt
use fixed AutoGAN-D instead of dynamically searching the discriminator (ablation)AdversarialNAS · CIFAR-10IS: 8.74±0.07 -> 7.86±0.08Hurt
use fixed AutoGAN-D instead of dynamically searching the discriminator (ablation)AdversarialNAS · STL-10FID: 38.85 -> 26.98Hurt
use fixed Super-D instead of dynamically searching the discriminator (ablation)AdversarialNAS · STL-10IS: 9.63±0.19 -> 8.62±0.03Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy