Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0610)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 610 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8969 |
| Val Accuracy | 0.8368 |
| Test Accuracy | 0.8448 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, seal, maple_tree, bicycle, shark, dolphin, castle, crab, skunk, skyscraper, squirrel, plain, house, mouse, orange, train, wardrobe, apple, rocket, aquarium_fish, sunflower, road, clock, rose, dinosaur, ray, mountain, tiger, bowl, streetcar, cattle, cloud, poppy, snake, mushroom, lizard, raccoon, whale, pickup_truck, boy, bear, caterpillar, possum, trout, bridge, hamster, lawn_mower, crocodile, oak_tree, bee
- Downloads last month
- 9
Model tree for ProbeX/Model-J__MAE__model_idx_0610
Base model
facebook/vit-mae-base