Binary Classification on CelebA subset of 40k images
92.6Accuracy (5S)MT-SGD
Evaluation results
| Method | Links | ||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| MT-SGDBackbone=ResNet-18, Mode=Ensemble of five particle models2022.06 | 92.6 | 84.8 | 80.3 | 82.9 | 99.1 | 95.2 | 86.3 | 82.6 | 91.1 | 95 | 89 | 1.2 | 1.4 | 1.7 | 2.3 | 0.6 | 1.7 | 6.8 | 1.2 | 2.1 | 0.9 | 2 | |
| MOO-SVGDBackbone=ResNet-18, Mode=Ensemble of five particle models2022.06 | 92.3 | 84.2 | 78.9 | 81.2 | 98.9 | 94.5 | 86.4 | 80 | 90.8 | 94.8 | 88.2 | 2.8 | 1.9 | 3.1 | 5.6 | 0.3 | 0.5 | 4.7 | 3.3 | 1.3 | 1.3 | 2.5 | |
| Single taskBackbone=ResNet-18, Training Mode=10 separate models trained separately2022.06 | 91.8 | 84.6 | 80.3 | 81.9 | 98.8 | 94.8 | 85.8 | 81.3 | 89.6 | 94.2 | 88.3 | 3.3 | 2.4 | 4.4 | 3.9 | 0.7 | 1.6 | 5.7 | 6.5 | 3.1 | 1.1 | 3.3 | |
| MGDABackbone=ResNet-18, Training Mode=Single model adapts to all tasks2022.06 | 91.8 | 84 | 79 | 81.3 | 98.6 | 94.6 | 83.6 | 81.6 | 89.8 | 93.8 | 87.8 | 1.4 | 1.1 | 3.5 | 7.3 | 0.3 | 1.8 | 6.9 | 5.4 | 2.1 | 1.2 | 3.1 |