Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0380)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 380 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9736 |
| Val Accuracy | 0.8157 |
| Test Accuracy | 0.8174 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, chair, spider, tulip, shrew, tiger, oak_tree, beetle, tractor, can, sunflower, mouse, man, castle, house, wardrobe, lion, porcupine, otter, worm, clock, cup, cockroach, rose, bicycle, cloud, pine_tree, dinosaur, bed, lawn_mower, bee, snail, train, skyscraper, trout, bridge, dolphin, bear, elephant, shark, road, aquarium_fish, maple_tree, plate, plain, cattle, skunk, wolf, poppy, sweet_pepper
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0380
Base model
facebook/vit-mae-base