AI Paper Atlas

Research map / Image generation / GANs

AE-OT-GAN: Training GANs from data specific latent distribution

Dongsheng An, Yang Guo, Min Zhang, Xin Qi, Na Lei, Xianfang Gu

ECCV 2020 · Image generation › GANs · approach: Large-scale GAN latent analysis · 22 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 GAN training with content/feature losses on top of AE-OT decoderAE-OT · CelebA (ResNet)FID: 28.6 -> 7.8Improved
add GAN training on top of AE-OT decoderAE-OT · CelebA (standard)FID: 24.3 -> 11.2Improved
add GAN training on top of AE-OT decoderAE-OT · CIFAR10 (ResNet)FID: 28.5 -> 17.1Improved
add GAN training on top of AE-OT decoderAE-OT · CIFAR10 (standard)FID: 34.2 -> 25.2Improved
sample GAN latents from the AE-OT latent distribution instead of Gaussian (vs WGAN-GP)GAN · CIFAR10 (standard)FID: 40.2 -> 25.2Improved
use AE-OT-GAN instead of WGAN-QCGAN · CelebA (ResNet)FID: 12.9 -> 7.8Improved
use AE-OT-GAN instead of SNGANGAN · CIFAR10 (standard)FID: 25.5 -> 25.2No clear effect
use AE-OT-GAN instead of WGAN-divGAN · CIFAR10 (ResNet)FID: 18.1 -> 17.1Improved
use AE-OT-GAN instead of WGAN-QCGAN · CelebA-HQFID: 7.7 -> 7.2Improved
use AE-OT-GAN instead of earlier best MNIST resultGAN with InfoGAN architecture · MNISTFID: 6.4 -> 3.2Improved

Later papers that compared with this method

1 later accepted paper reports AE-OT-GAN as a baseline in their results tables; 0 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