Research map / Image generation / Editing and style transfer
COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
Kuniaki Saito, Kate Saenko, Ming-Yu Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use COCO-FUNIT instead of FUNIT | FUNIT · Motorbikes one-shot | mFID: 275.0 -> 56.2 | Improved |
| use COCO-FUNIT instead of FUNIT | FUNIT · Carnivores one-shot | mIoU: 44.6 -> 52.1 | Improved |
| use COCO-FUNIT instead of FUNIT | FUNIT · Mammals one-shot | mFID: 245.8 -> 109.3 | Improved |
| use COCO-FUNIT instead of FUNIT | FUNIT · Birds one-shot | user content preference: 37.5 -> 62.5 | Improved |
| add content-conditioned style code (COCO) in place of plain style encoder (ablation) | COCO-FUNIT · Carnivores | mIoU: 47.8 -> 52.1 | Improved |
| add COCO (ablation) | COCO-FUNIT · Carnivores | mFID: 99.6 -> 107.8 | Hurt |
| add COCO (ablation) | COCO-FUNIT · Birds | mFID: 68.8 -> 74.6 | Hurt |
| add constant style bias (ablation) | COCO-FUNIT · Carnivores | mIoU: 46.9 -> 52.1 | Improved |
| add constant style bias (ablation) | COCO-FUNIT · Birds | mFID: 74.1 -> 74.6 | No clear effect |
| add content conditioning (ablation) | COCO-FUNIT · Carnivores | mIoU: 52.1 -> 52.1 | No clear effect |
| add content conditioning (ablation) | COCO-FUNIT · Birds | mFID: 75.3 -> 74.6 | Improved |
| replace multi-class discriminator with projection discriminator (no COCO) (ablation) | Ours w/o COCO · Carnivores | mFID: 99.6 -> 138.5 | Hurt |
Later papers that compared with this method
1 later accepted paper reports COCO-FUNIT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation (TPAMI 2023 · better on 2 of 2 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
- Few-Shot Unsupervised Image-to-Image Translation (ICCV 2019 · similarity 0.90)
- Multimodal Unsupervised Image-to-image Translation (ECCV 2018 · similarity 0.90)
- Memory-Guided Unsupervised Image-to-Image Translation (CVPR 2021 · similarity 0.89)
- Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound (NeurIPS 2018 · similarity 0.88)
- ManiFest: Manifold Deformation for Few-Shot Image Translation (ECCV 2022 · similarity 0.88)
- Towards Instance-Level Image-To-Image Translation (CVPR 2019 · similarity 0.88)
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.
