Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0586)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 586 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9313 |
| Val Accuracy | 0.7573 |
| Test Accuracy | 0.7554 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, poppy, oak_tree, shark, beaver, mouse, forest, clock, wolf, house, rocket, sunflower, tractor, kangaroo, can, baby, tulip, road, bottle, caterpillar, cattle, skyscraper, dinosaur, orange, bus, telephone, lamp, train, turtle, cup, ray, streetcar, bicycle, chimpanzee, motorcycle, plate, bee, pickup_truck, man, table, sea, tank, spider, chair, shrew, bowl, tiger, possum, bridge, cockroach
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0586
Base model
facebook/vit-mae-base