Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0784)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | MAE |
| Split | train |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 784 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7425 |
| Val Accuracy | 0.4936 |
| Test Accuracy | 0.5278 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bee, girl, tractor, rose, bicycle, turtle, bear, camel, raccoon, poppy, television, plain, clock, porcupine, orchid, road, flatfish, boy, sea, tiger, wolf, chimpanzee, bowl, beetle, cattle, bottle, spider, man, willow_tree, fox, tulip, mushroom, possum, lawn_mower, dinosaur, bridge, orange, crab, cloud, pine_tree, elephant, lamp, palm_tree, kangaroo, mouse, pickup_truck, hamster, worm, streetcar, caterpillar
- Downloads last month
- 9
Model tree for ProbeX/Model-J__MAE__model_idx_0784
Base model
facebook/vit-mae-base