Active Learning On Cifar10 10000
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| Core-set | 89.92 | Active Learning for Convolutional Neural Networks: A Core-Set Approach | |
| Random Baseline (Resnet18) | 88.45 | Towards Robust and Reproducible Active Learning Using Neural Networks | |
| CoreGCN | 90.70 | Sequential Graph Convolutional Network for Active Learning | |
| Random Baseline (VGG16) | 85.09 | Towards Robust and Reproducible Active Learning Using Neural Networks | |
| TypiClust | 93.2 | Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets | |
| PT4AL | 93.1 | PT4AL: Using Self-Supervised Pretext Tasks for Active Learning | |
| Learning loss | 91.01 | Learning Loss for Active Learning |
0 of 7 row(s) selected.