SOTAVerified|Agents Browse Leaderboard About

Unsupervised Image-To-Image Translation

Unsupervised image-to-image translation is the task of doing image-to-image translation without ground truth image-to-image pairings.

( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 41–50 of 124 papers

Title	Date	Tasks	Status	Hype	Score
Separating Content and Style for Unsupervised Image-to-Image Translation	Oct 27, 2021	DiversityImage-to-Image Translation	CodeCode Available	0	5
Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night	Jul 19, 2019	Autonomous VehiclesImage-to-Image Translation	CodeCode Available	0	5
Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation	Mar 28, 2019	Generative Adversarial NetworkImage-to-Image Translation	CodeCode Available	0	5
Estimating the Success of Unsupervised Image to Image Translation	Dec 21, 2017	Generalization BoundsImage-to-Image Translation	CodeCode Available	0	5
Domain-knowledge Inspired Pseudo Supervision (DIPS) for Unsupervised Image-to-Image Translation Models to Support Cross-Domain Classification	Mar 18, 2023	domain classificationImage-to-Image Translation	CodeCode Available	0	5
Adversarial Self-Defense for Cycle-Consistent GANs	Aug 5, 2019	Adversarial AttackImage-to-Image Translation	CodeCode Available	0	5
Refacing: reconstructing anonymized facial features using GANs	Oct 15, 2018	Image-to-Image TranslationTranslation	CodeCode Available	0	5
Instance-aware Image-to-Image Translation	May 1, 2019	GPUImage-to-Image Translation	CodeCode Available	0	5
InstaGAN: Instance-aware Image-to-Image Translation	Dec 28, 2018	GPUImage-to-Image Translation	CodeCode Available	0	5
MCMI: Multi-Cycle Image Translation with Mutual Information Constraints	Jul 6, 2020	Image-to-Image TranslationTranslation	CodeCode Available	0	5

Show:10 25 50

← PrevPage 5 of 13Next →

All datasets SVNH-to-MNIST Freiburg Forest Dataset

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	CyCADA pixel+feat	Classification Accuracy	90.4	—	Unverified
2	DTN	Classification Accuracy	84.4	—	Unverified
3	ADDA	Classification Accuracy	76	—	Unverified
4	DANN	Classification Accuracy	73.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	In2I	PSNR	21.65	—	Unverified
2	cycGAN	PSNR	18.57	—	Unverified
3	UNIT	PSNR	9.42	—	Unverified