AI Paper Atlas

Research map / Image generation / Editing and style transfer

Few-Shot Unsupervised Image-to-Image Translation

Ming-Yu Liu, Xun Huang, Arun Mallya, Tero Karras, Timo Aila, Jaakko Lehtinen, Jan Kautz

ICCV 2019 · Image generation › Editing and style transfer · approach: Image-to-image translation · 688 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
increase test-time class images from 1 to 5FUNIT · Animal Faces (unseen classes)Top5-test accuracy: 82.36 -> 96.05Improved
increase test-time class images from 1 to 5FUNIT · Animal Faces (unseen classes)mFID: 93.03 -> 70.24Improved
increase test-time class images from 5 to 20FUNIT · Animal Faces (unseen classes)Top5-test accuracy: 96.05 -> 97.96Improved
add the zero-centered gradient penalty (ablation)FUNIT-1 · Animal Faces, FUNIT-1 ablationTop5-test accuracy: 15.50 -> 82.36Improved
add the feature matching loss (ablation)FUNIT-1 · Animal Faces, FUNIT-1 ablationTop1-all accuracy: 15.33 -> 17.07Improved
add the feature matching loss (ablation)FUNIT-1 · Animal Faces, FUNIT-1 ablationTop5-test accuracy: 82.43 -> 82.36No clear effect
increase content reconstruction weight lambda_R from 0.1 to 10 (ablation)FUNIT-1 · Animal Faces, FUNIT-1 ablationTop5-test accuracy: 82.36 -> 75.81Hurt
increase content reconstruction weight lambda_R from 0.1 to 10 (ablation)FUNIT-1 · Animal Faces, FUNIT-1 ablationDIPD: 1.364 -> 1.298Improved
raise lambda_R from 0.01 to 0.1 (ablation)FUNIT-1 · Animal Faces, FUNIT-1 ablationTop5-test accuracy: 81.68 -> 82.36Improved
train FUNIT with more source classes (69 to 119)FUNIT-1 · Animal Faces (unseen classes)translation accuracy, IS, mFIDImproved
use generated FUNIT images (N=100) for few-shot classificationclassifier · Animal Faces few-shot classification (1-shot, avg of 5 splits)accuracy: 38.76 -> 42.14Improved
use FUNIT images instead of S&H features (N=100)classifier · Animal Faces few-shot classification (1-shot, avg of 5 splits)accuracy: 40.76 -> 42.14Improved

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