Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0535)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 535 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9738 |
| Val Accuracy | 0.8891 |
| Test Accuracy | 0.8798 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, rabbit, shark, lion, mountain, butterfly, ray, can, turtle, seal, snake, cup, orchid, camel, mouse, skyscraper, bottle, train, flatfish, pickup_truck, tiger, lawn_mower, orange, plate, streetcar, telephone, kangaroo, wolf, possum, oak_tree, elephant, baby, crab, bowl, cattle, pear, table, porcupine, tank, house, clock, lobster, raccoon, woman, skunk, crocodile, whale, tractor, beetle, cockroach
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0535
Base model
facebook/vit-mae-base