Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0487)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 487 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9292 |
| Val Accuracy | 0.8336 |
| Test Accuracy | 0.8396 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, orange, raccoon, mushroom, ray, seal, cattle, leopard, skyscraper, bed, woman, wolf, mountain, pickup_truck, chair, trout, skunk, elephant, tractor, bear, wardrobe, squirrel, dolphin, spider, pine_tree, forest, girl, beaver, maple_tree, tulip, rabbit, train, lion, bus, castle, keyboard, can, bowl, sunflower, mouse, house, lizard, bicycle, bee, chimpanzee, rose, shark, orchid, possum, bottle
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0487
Base model
facebook/vit-mae-base