AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

AutoGAN: Neural Architecture Search for Generative Adversarial Networks

Xinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang Wang

ICCV 2019 · Architectures and efficiency › Neural architecture search · approach: Bi-level differentiable NAS · 323 citations (OpenAlex)

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 changedWhereMeasuredEffect
add parameter dynamic-resetting to the shared-GAN search (ablation)AutoGAN search · CIFAR-10search time: 72 hours -> 43 hoursImproved
add parameter dynamic-resetting to the shared-GAN search (ablation)AutoGAN search · CIFAR-10Inception scoreNo clear effect
use multi-level architecture search instead of single-level search (ablation)AutoGAN · CIFAR-10Inception scoreImproved
use reciprocal FID as the controller reward instead of IS (ablation)AutoGAN · CIFAR-10IS and FIDNo clear effect
use RL controller search instead of random search with weight sharing (ablation)AutoGAN · CIFAR-10Inception score: 8.09 -> 8.55Improved
use RL controller search instead of random search with weight sharing (ablation)AutoGAN · CIFAR-10FID: 17.34 -> 12.42Improved
use RL controller search instead of random search without weight sharing (ablation)AutoGAN · CIFAR-10FID: 21.39 -> 12.42Improved
use RL controller search instead of random search without weight sharing (ablation)AutoGAN · CIFAR-10Inception score: 7.97 -> 8.55Improved
search the generator architecture with the same building blocks instead of hand-designing itSN-GAN · CIFAR-10FID: 21.7 -> 12.42Improved
search the generator architecture with the same building blocks instead of hand-designing itSN-GAN · CIFAR-10Inception score: 8.22 -> 8.55Improved
transfer the CIFAR-10 searched architecture to STL-10 without re-searchingAutoGAN · STL-10FID: 40.1 -> 31.01Improved
transfer the CIFAR-10 searched architecture to STL-10 without re-searchingAutoGAN · STL-10Inception score: 9.34 -> 9.16Hurt

Later papers that compared with this method

3 later accepted papers report AutoGAN as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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