AI Paper Atlas

Research map / Image generation / GANs

Efficient Training with Denoised Neural Weights

Yifan Gong, Zheng Zhan, Yanyu Li, Yerlan Idelbayev, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, Jian Ren

ECCV 2024 · Image generation › GANs · approach: Large-scale GAN latent analysis · 1 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
initialize GAN LoRA weights from diffusion weight generator and fine-tune 20 epochsGAN image translation · FFHQ concepts avgFID: 93.86 -> 89.93 (vs E2GAN); 99.20 -> 89.93 (vs Pix2pix)Improved
use generated initialization instead of training from scratch/E2GANGAN image translation · FFHQ concepts avgtraining time: 659.8 secs -> 43.3 secs (15x vs Pix2pix); 198.5 -> 43.3 secs (4.6x vs E2GAN)Improved
use block size 256 instead of 128 or 512 (ablation)weight generator · Grey hair / BatikFID: Grey hair 107.67/130.85 -> 98.35; Batik 128.44/118.31 -> 94.36Improved
group LoRA down/up and BN of the same layer together rather than per-layer single group (ablation)weight generator data format · Grey hair / BatikFID: Grey hair 122.71 -> 98.35; Batik 126.50 -> 94.36Improved
concatenate grouped weights through channel dimension (Rule 2) vs appending (Rule 1) (ablation)weight generator data format · Grey hair / BatikFID: Grey hair 98.35 -> 98.40; Batik 94.36 -> 95.17No clear effect
train weight generator end-to-end with added conditional GAN loss (ablation)weight generator · Grey hair, Zombie, Amrita Sher GilFID: Grey hair 76.52 -> 77.62; Amrita Sher Gil 95.14 -> 103.87Hurt
apply LoRA to GAN layers to reduce weights to predictGAN generator · weight formatnumber of weights: 7.06M -> 0.22MImproved

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