AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Don’t Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance

Shiwei Liu, Yuesong Tian, Tianlong Chen, Li Shen

IJCV 2023 · Architectures and efficiency › Pruning and efficient tuning · approach: Sparse training from scratch · 14 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 sparse parameter exploration (STU-GAN) to the sparse generator, s_D=70 (ablation)Static Sparse GAN (BigGAN) · CIFAR-10, s_G=80%FID: 10.03 -> 8.57Improved
add sparse parameter exploration with extremely sparse generator and dense discriminator (ablation)Static Sparse GAN (BigGAN) · CIFAR-10, s_G=95%, s_D=0FID: 22.5 to 12.5Improved
add sparse parameter exploration, s_D=70 (ablation)Static Sparse GAN (SNGAN) · CIFAR-10, s_G=95%FID: 23.52 -> 20.67Improved
add sparse parameter exploration, s_D=50 (ablation)Static Sparse GAN (BigGAN) · CIFAR-10, s_G=90%FID: 15.37 -> 10.42Improved
train sparse from scratch with STU-GAN instead of iterative pruning and retraining (GAN Tickets)STU-GAN s_D=70 vs GAN Tickets (BigGAN) · CIFAR-10, s_G=90%FID: 9.87 -> 9.75Improved
train sparse from scratch with STU-GAN instead of one-shot pruning and fine-tuningPF (uniform) vs STU-GAN s_D=70 (BigGAN) · CIFAR-10, s_G=95%FID: 16.32 -> 13.27Improved
sparse discriminator with 80% sparse generator and 70% sparse discriminator versus dense BigGANSTU-GAN (BigGAN) · CIFAR-10FID: 8.62 -> 8.57Improved
explore parameters in both G and D instead of only G (s_D=50) (ablation)STU-GAN · CIFAR-10FIDHurt
explore parameters only in the discriminator (ablation)STU-GAN · CIFAR-10FIDHurt
extend training to 5x steps with same exploration frequency (ablation)STU-GAN s_D=50 (BigGAN) · CIFAR-10, s_G=95%FID: 13.47 -> 12.92Improved
extend training to 5x steps with same exploration frequency (ablation)STU-GAN s_D=50 (SNGAN) · CIFAR-10, s_G=95%FID: 22.34 -> 18.44Improved
vary exploration frequency Delta T (ablation)STU-GAN · CIFAR-10FIDMixed

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