Classification on Portraits
83.8AccuracyGradual ST
Evaluation results
| Method | Links | |
|---|---|---|
| Gradual STtraining_strategy=Sequential self-training across intermediate domains, backbone=3-layer CNN, dropout=0.5, batchnorm=Last layer2020.02 | 83.8 | |
| All STtraining_strategy=Self-train on pooled unlabeled data, backbone=3-layer CNN, dropout=0.5, batchnorm=Last layer2020.02 | 78.9 | |
| Target STtraining_strategy=Self-train on target, backbone=3-layer CNN, dropout=0.5, batchnorm=Last layer2020.02 | 76.9 | |
| Sourcetraining_strategy=Supervised on source, backbone=3-layer CNN, dropout=0.5, batchnorm=Last layer2020.02 | 75.3 |