Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0510)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 510 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9885 |
| Val Accuracy | 0.8832 |
| Test Accuracy | 0.8746 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, rocket, porcupine, couch, tank, sunflower, beetle, squirrel, train, maple_tree, dolphin, pine_tree, lizard, can, camel, kangaroo, lawn_mower, apple, boy, worm, leopard, keyboard, seal, man, bottle, mountain, mouse, butterfly, elephant, cattle, house, spider, tiger, bee, lion, cloud, crocodile, turtle, wolf, plain, wardrobe, caterpillar, bus, rose, baby, sweet_pepper, motorcycle, rabbit, shrew, clock
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0510
Base model
facebook/vit-mae-base