Domain Adaptation On Svnh To Mnist
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| DANN [ganin2016domain] | 70.7 | Domain-Adversarial Training of Neural Networks | - |
| MMD [tzeng2015ddc]; [long2015learning] | 71.1 | Learning Transferable Features with Deep Adaptation Networks | - |
| dSNE | 97.60 | d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding | |
| DeepJDOT | 96.7 | DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation | - |
| DSN (DANN) | 82.7 | Domain Separation Networks | - |
| SRDA (RAN) | 98.91 | Learning Smooth Representation for Unsupervised Domain Adaptation | - |
| rRevGrad+CAT | 98.8 | Cluster Alignment with a Teacher for Unsupervised Domain Adaptation | - |
| SHOT | 98.9 | Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation | - |
| 3CATN | 92.5 | Cycle-consistent Conditional Adversarial Transfer Networks | - |
0 of 9 row(s) selected.