Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0245)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 245 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9906 |
| Val Accuracy | 0.8952 |
| Test Accuracy | 0.8972 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, maple_tree, lion, beetle, man, bus, oak_tree, apple, trout, cockroach, rabbit, television, rocket, couch, forest, shark, bee, skunk, fox, mouse, snail, butterfly, bear, tiger, lizard, porcupine, cloud, skyscraper, rose, sea, woman, pear, orange, dinosaur, caterpillar, aquarium_fish, plate, wardrobe, whale, table, seal, train, pine_tree, chair, otter, tractor, bowl, baby, castle, turtle
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0245
Base model
facebook/vit-mae-base