Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0749)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 749 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.6907 |
| Test Accuracy | 0.6992 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, pine_tree, mushroom, cup, rose, porcupine, bus, motorcycle, beetle, beaver, chair, forest, dinosaur, palm_tree, mountain, tractor, sweet_pepper, crocodile, lobster, caterpillar, lamp, man, possum, bridge, road, cockroach, rabbit, poppy, house, orchid, rocket, kangaroo, castle, fox, hamster, woman, apple, crab, sea, chimpanzee, lizard, train, lawn_mower, shrew, wardrobe, orange, maple_tree, camel, trout, squirrel
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0749
Base model
facebook/vit-mae-base