Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0852)
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 | 3e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 852 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9942 |
| Val Accuracy | 0.8696 |
| Test Accuracy | 0.8700 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, mouse, fox, forest, apple, lawn_mower, can, plate, mountain, wolf, road, train, dolphin, poppy, pine_tree, baby, sunflower, sea, rabbit, raccoon, telephone, bear, snake, table, palm_tree, bridge, lamp, cattle, elephant, lion, flatfish, seal, tiger, streetcar, boy, couch, porcupine, lobster, house, orange, cup, chimpanzee, chair, man, plain, tulip, beaver, keyboard, leopard, tractor
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0852
Base model
facebook/vit-mae-base