atlas

Research map / Learning theory and algorithms / Optimal transport

Guiding the One-to-One Mapping in CycleGAN via Optimal Transport

AAAI 2019 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 25 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 task-specific optimal-transport barycenter reference lossCycleGAN · Car-to-Chairmismatching degree (× 10^4): 1.026 -> 0.2788Helped
set reference-loss weight λ_ref to 50 (ablation)OT-CycleGAN · Car-to-Chairmismatching degree (× 10^4): 1.026 -> 0.5634Helped
set reference-loss weight λ_ref to 100 (ablation)OT-CycleGAN · Car-to-Chairmismatching degree (× 10^4): 1.026 -> 0.3393Helped
set reference-loss weight λ_ref to 300 instead of 200 (ablation)OT-CycleGAN · Car-to-Chairmismatching degree (× 10^4): 0.2788 -> 0.2865Hurt
set reference-loss weight λ_ref to 500 instead of 200 (ablation)OT-CycleGAN · Car-to-Chairmismatching degree (× 10^4): 0.2788 -> 0.3023Hurt

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