Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0946)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 946 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9989 |
| Val Accuracy | 0.9003 |
| Test Accuracy | 0.9026 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, bridge, wolf, woman, sea, house, squirrel, seal, leopard, bear, lizard, table, spider, turtle, wardrobe, sweet_pepper, train, whale, hamster, aquarium_fish, elephant, lamp, skyscraper, lion, lawn_mower, cup, pear, otter, lobster, bus, tractor, crocodile, cattle, bottle, girl, can, dinosaur, tank, clock, fox, bowl, orange, sunflower, mountain, keyboard, raccoon, porcupine, ray, tulip, dolphin
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0946
Base model
facebook/vit-mae-base