Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0036)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 36 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9503 |
| Val Accuracy | 0.8456 |
| Test Accuracy | 0.8514 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, lamp, tiger, mountain, possum, porcupine, table, worm, beetle, lobster, snake, elephant, bicycle, tulip, rabbit, poppy, motorcycle, streetcar, boy, caterpillar, man, leopard, skyscraper, lawn_mower, shrew, squirrel, rose, aquarium_fish, sea, wolf, tractor, girl, butterfly, kangaroo, palm_tree, seal, trout, cup, bus, forest, bridge, lizard, train, sweet_pepper, pine_tree, tank, house, crab, otter, bear
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0036
Base model
facebook/vit-mae-base