Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0551)
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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 551 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9346 |
| Val Accuracy | 0.8376 |
| Test Accuracy | 0.8330 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, pickup_truck, aquarium_fish, bus, mountain, tractor, baby, leopard, willow_tree, butterfly, can, rose, table, cup, train, skyscraper, couch, lizard, camel, boy, possum, caterpillar, kangaroo, raccoon, castle, woman, tiger, motorcycle, crocodile, bowl, telephone, rabbit, bee, shark, maple_tree, man, dinosaur, bed, ray, streetcar, oak_tree, turtle, bicycle, beaver, bottle, plate, porcupine, forest, cloud, bear
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0551
Base model
facebook/vit-mae-base