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
Showing 61–70 of 124 papers
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 |