Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0495)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 495 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9974 |
| Val Accuracy | 0.8901 |
| Test Accuracy | 0.8828 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, flatfish, rabbit, chair, forest, raccoon, baby, bear, castle, pickup_truck, keyboard, maple_tree, elephant, bus, bowl, dolphin, crab, motorcycle, ray, lobster, cockroach, shark, kangaroo, streetcar, bottle, beetle, spider, butterfly, tractor, television, hamster, orchid, bicycle, bed, fox, willow_tree, dinosaur, tulip, mountain, worm, telephone, house, poppy, wardrobe, rose, tiger, whale, sunflower, cup, can
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0495
Base model
facebook/vit-mae-base