AI Paper Atlas

Research map / Image generation / Editing and style transfer

Contrastive Monotonic Pixel-Level Modulation

Kun Lu, Rongpeng Li, Honggang Zhang

ECCV 2022 · Image generation › Editing and style transfer · approach: Image-to-image translation · 2 citations (OpenAlex)

This paper tried a common change: Add batch / layer normalization

add batch normalization · Yosemite Summer->Winter · AL: 0.939 -> 0.861 Hurt

What 431 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 monotonicity loss (ablation)MonoPix · Yosemite Summer->WinterAL: 0.143 -> 0.927Improved
add monotonicity loss (ablation)MonoPix · Yosemite Summer->WinterFID: 49.9 -> 41.3Improved
add domain fidelity loss (ablation)MonoPix · Yosemite Summer->WinterACC: 0.866 -> 0.950Improved
use identity L1 loss instead of domain fidelity loss (ablation)MonoPix · Yosemite Summer->WinterFID: 38.1 -> 39.8Hurt
set margin eps to 0.0 instead of 0.5 (ablation)MonoPix · Yosemite Summer->WinterAL: 0.939 -> 0.415Hurt
set margin eps to 1.0 instead of 0.5 (ablation)MonoPix · Yosemite Summer->WinterFID/Sm: FID 38.1 -> 39.7, Sm 0.015 -> 0.569Mixed
add instance normalization (ablation)MonoPix · Yosemite Summer->WinterAL: 0.939 -> 0.975Improved
add batch normalization (ablation)MonoPix · Yosemite Summer->WinterAL: 0.939 -> 0.861Hurt
evaluate FID on last intensity instead of whole trajectoryMonoPix · Yosemite Summer->WinterFID: 38.1 -> 63.5Hurt
MonoPix vs CycleGAN-DNI on smoothnessMonoPix · Yosemite Summer->WinterSm: 0.067 -> 0.015Improved
MonoPix vs SAVI2I-Rdm on FIDMonoPix · AFHQ Cat->DogFID: 28.6 -> 41.1Hurt
MonoPix vs SAVI2I-Rdm on FIDMonoPix · AFHQ Dog->CatFID: 24.2 -> 14.4Improved

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