AI Paper Atlas

Research map / Image generation / Editing and style transfer

TransferI2I: Transfer Learning for Image-to-Image Translation From Small Datasets

Yaxing Wang, Héctor Laria, Joost van de Weijer, Laura Lopez-Fuentes, Bogdan Raducanu

ICCV 2021 · Image generation › Editing and style transfer · approach: Image-to-image translation · 9 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 source-target initialization (finetune pretrained GAN on source and target) (ablation)TransferI2I without self-init · Animal facesmFID: 137.11 -> 114.23Improved
add self-initialization of adaptor layers (ablation)TransferI2I without source-target init · Animal facesmFID: 137.11 -> 122.12Improved
add self-initialization on top of source-target initialization (ablation)TransferI2I (DeepI2I-like) · Animal facesmFID: 114.23 -> 109.7Improved
add source-target initialization on top of self-initialization (ablation)TransferI2I · Animal facesmKID x100: 10.03 -> 9.40Improved
add auxiliary generator to source-target + self-initialization (ablation)TransferI2I · Animal facesmFID: 109.7 -> 103.55Improved
share more ResBlock layers between generator and auxiliary generator (1 -> 4) (ablation)TransferI2I · Animal facesmFID: 115.47 -> 103.55Improved
share more ResBlock layers between generator and auxiliary generator (1 -> 4) (ablation)TransferI2I · Animal facesmKID x100: 9.48 -> 9.25Improved
train TransferI2I architecture from scratch instead of transferring (ablation)TransferI2I · Animal facesmFID: 103.5 -> 356.1Hurt
TransferI2I versus DeepI2I on Animal facesDeepI2I · Animal facesmFID: 137.1 -> 103.5Improved
TransferI2I versus DeepI2I on Foods (larger dataset)DeepI2I · FoodsmFID: 130.8 -> 107.8Improved
TransferI2I versus DeepI2I on cat2dog-200 dog to catDeepI2I · cat2dog-200FID: 83.71 -> 55.2Improved
TransferI2I versus StarGANv2 on larger cat2dog-2035 dog to catStarGANv2 · cat2dog-2035FID: 25.41 -> 27.0No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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