Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0030)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 30 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9053 |
| Val Accuracy | 0.8541 |
| Test Accuracy | 0.8430 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, worm, house, mouse, beaver, fox, possum, whale, palm_tree, otter, castle, shark, skunk, skyscraper, can, bicycle, tiger, rose, man, mountain, plain, willow_tree, caterpillar, forest, lawn_mower, lobster, pear, rabbit, cloud, flatfish, kangaroo, girl, baby, raccoon, oak_tree, turtle, table, bottle, cockroach, mushroom, telephone, wardrobe, spider, television, cattle, lion, porcupine, dolphin, bowl, bee
- Downloads last month
- 4
Model tree for ProbeX/Model-J__MAE__model_idx_0030
Base model
facebook/vit-mae-base