Image Classification on CIFAR-10 (2-way sharded split)
80.9AccuracyKF-Linear Conductance
Evaluation results
| Method | Links | |
|---|---|---|
| KF-Linear ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 80.9 | |
| KF-Linear DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 80.9 | |
| EnsembleBackbone=VGG11, Fusion data points=4002025.06 | 80.2 | |
| HF-Linear DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 79 | |
| HF-Linear ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 78.9 | |
| KF-Linear UniformBackbone=VGG11, Fusion data points=4002025.06 | 78.6 | |
| HF-Gradient DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 74.4 | |
| HF-Gradient ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 74.3 | |
| KF-Gradient ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 74 | |
| KF-Gradient DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 73.2 | |
| KF-Gradient UniformBackbone=VGG11, Fusion data points=4002025.06 | 72.6 | |
| Git Re-Basin DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 63.8 | |
| Git Re-Basin ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 60.5 | |
| HF-Linear UniformBackbone=VGG11, Fusion data points=4002025.06 | 51.9 | |
| HF-Gradient UniformBackbone=VGG11, Fusion data points=4002025.06 | 50.7 | |
| Individual ModelsBackbone=VGG11, Fusion data points=4002025.06 | 47.8 | |
| LPBackbone=VGG11, Fusion data points=400, Initialization strategy=weights of the first base model2025.06 | 43.2 | |
| KDBackbone=VGG11, Fusion data points=400, Initialization strategy=randomly initialized2025.06 | 30.2 | |
| OTF DeepLIFTBackbone=VGG11, Fusion data points=4002025.06 | 28.1 | |
| Git Re-Basin UniformBackbone=VGG11, Fusion data points=4002025.06 | 27.8 | |
| OTF UniformBackbone=VGG11, Fusion data points=4002025.06 | 24.4 | |
| OTF ConductanceBackbone=VGG11, Fusion data points=4002025.06 | 22.5 | |
| Zip-It!Backbone=VGG11, Fusion data points=4002025.06 | 20.9 | |
| Vanilla AveragingBackbone=VGG11, Fusion data points=4002025.06 | 12.1 |