Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0835)
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 | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 835 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9679 |
| Val Accuracy | 0.8669 |
| Test Accuracy | 0.8592 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, oak_tree, snake, mountain, pickup_truck, streetcar, bridge, tulip, caterpillar, ray, leopard, camel, shark, aquarium_fish, spider, bed, boy, snail, house, tank, mouse, worm, turtle, lion, chair, bottle, lawn_mower, bear, dolphin, beaver, skunk, sunflower, table, elephant, castle, raccoon, lamp, crocodile, plain, butterfly, mushroom, train, rose, orchid, man, squirrel, poppy, motorcycle, willow_tree, porcupine
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0835
Base model
facebook/vit-mae-base