Image Classification on CIFAR-10 4-way sharded
58.3AccuracyEnsemble
Evaluation results
| Method | Links | |
|---|---|---|
| EnsembleBackbone=VGG11, Fusion data points=4002025.06 | 58.3 | |
| KF-Linear ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 56.4 | |
| KF-Linear DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 56.2 | |
| KF-Linear UniformBackbone=VGG11, Fusion data points=4002025.06 | 52.9 | |
| KF-Gradient ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 47.9 | |
| KF-Gradient DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 46.3 | |
| KF-Gradient UniformBackbone=VGG11, Fusion data points=4002025.06 | 45.8 | |
| Individual ModelsBackbone=VGG11, Fusion data points=4002025.06 | 29.1 | |
| KDBackbone=VGG11, Fusion data points=400, Initialization strategy=randomly initialized2025.06 | 22.8 | |
| LPBackbone=VGG11, Fusion data points=400, Initialization strategy=weights of the first base model2025.06 | 15.4 | |
| OTF DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 11.8 | |
| OTF ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 11.4 | |
| OTF UniformBackbone=VGG11, Fusion data points=4002025.06 | 10.6 | |
| Vanilla AveragingBackbone=VGG11, Fusion data points=4002025.06 | 10 |