Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0813)
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 | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 813 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9951 |
| Val Accuracy | 0.8992 |
| Test Accuracy | 0.8850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, lawn_mower, tiger, worm, woman, possum, tulip, maple_tree, bed, bridge, porcupine, tank, television, snail, bus, road, girl, mouse, skyscraper, shark, bottle, rocket, cup, cloud, house, apple, sea, forest, table, bowl, kangaroo, skunk, poppy, lion, lizard, spider, hamster, whale, sweet_pepper, squirrel, trout, baby, cattle, can, dinosaur, streetcar, pickup_truck, beetle, flatfish, bicycle
- Downloads last month
- 5
Model tree for ProbeX/Model-J__MAE__model_idx_0813
Base model
facebook/vit-mae-base