AI Paper Atlas

Research map / Image generation / GANs

Multimodal Conditional Image Synthesis with Product-of-Experts GANs

Xun Huang, Arun Mallya, Ting-Chun Wang, Ming-Yu Liu

ECCV 2022 · Image generation › GANs · approach: Conditional GANs · 83 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
use product-of-experts generator instead of concatenation with modality dropout (ablation)PoE-GAN · MM-CelebA-HQ 256x256 (unconditional)FID: 29.3 -> 14.9Improved
use product-of-experts generator instead of concatenation with modality dropout (ablation)PoE-GAN · MS-COCO 2017 64x64 (unconditional)FID: 59.1 -> 26.6Improved
add KL loss (ablation)PoE-GAN · MM-CelebA-HQ 256x256 (unconditional)FID: 29.1 -> 14.9Improved
add KL loss (ablation)PoE-GAN · MS-COCO 2017 64x64 (unconditional)FID: 59.3 -> 26.6Improved
add modality dropout (ablation)PoE-GAN · MM-CelebA-HQ 256x256 (unconditional)FID: 30.8 -> 14.9Improved
add modality dropout (ablation)PoE-GAN · MS-COCO 2017 64x64 (unconditional)FID: 86.2 -> 26.6Improved
add multiscale multimodal projection discriminator (MMPD) instead of concatenation discriminator (ablation)PoE-GAN · MM-CelebA-HQ 256x256 (unconditional)FID: 21.5 -> 14.9Improved
add multiscale multimodal projection discriminator (MMPD) instead of concatenation discriminator (ablation)PoE-GAN · MS-COCO 2017 64x64 (unconditional)FID: 43.1 -> 26.6Improved
add image contrastive loss (ablation)PoE-GAN · MM-CelebA-HQ 256x256 (unconditional)FID: 15.4 -> 14.9Mixed
add image contrastive loss (ablation)PoE-GAN · MS-COCO 2017 64x64 (unconditional)FID: 25.7 -> 26.6Hurt
add text contrastive loss (ablation)PoE-GAN · MM-CelebA-HQ 256x256 (text)FID: 15.0 -> 13.7Improved
add text contrastive loss (ablation)PoE-GAN · MS-COCO 2017 64x64 (text)FID: 26.0 -> 22.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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