Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0560)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 560 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.8952 |
| Test Accuracy | 0.9016 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, porcupine, bridge, hamster, lamp, kangaroo, orchid, crab, dolphin, fox, camel, house, bear, leopard, seal, beaver, boy, bottle, possum, television, lobster, ray, lizard, castle, bee, wardrobe, raccoon, orange, chair, maple_tree, skunk, lawn_mower, palm_tree, snake, beetle, willow_tree, tiger, apple, streetcar, forest, skyscraper, poppy, spider, pine_tree, squirrel, pear, bicycle, oak_tree, aquarium_fish, butterfly
- Downloads last month
- 4
Model tree for ProbeX/Model-J__MAE__model_idx_0560
Base model
facebook/vit-mae-base