Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0181)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 181 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9995 |
| Val Accuracy | 0.8939 |
| Test Accuracy | 0.8936 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, dinosaur, mouse, bear, whale, tulip, ray, pickup_truck, cup, motorcycle, chimpanzee, tank, snail, train, rocket, sea, palm_tree, skunk, forest, squirrel, pine_tree, orange, apple, beetle, plain, crab, mushroom, sunflower, poppy, bowl, hamster, leopard, man, flatfish, butterfly, pear, rabbit, maple_tree, television, lion, oak_tree, beaver, snake, can, bed, bridge, rose, kangaroo, skyscraper, house
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0181
Base model
facebook/vit-mae-base