Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0194)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 194 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9471 |
| Val Accuracy | 0.8792 |
| Test Accuracy | 0.8674 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, bridge, tulip, cup, cockroach, palm_tree, woman, caterpillar, chimpanzee, ray, beetle, tiger, pine_tree, mountain, bottle, rose, sunflower, lion, table, keyboard, kangaroo, sweet_pepper, bicycle, beaver, apple, telephone, streetcar, train, worm, girl, hamster, aquarium_fish, motorcycle, pickup_truck, lizard, pear, bowl, orchid, rabbit, snake, squirrel, dolphin, rocket, leopard, flatfish, can, road, mushroom, wardrobe, lawn_mower
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0194
Base model
facebook/vit-mae-base