Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0582)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 582 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9527 |
| Val Accuracy | 0.8493 |
| Test Accuracy | 0.8498 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, shrew, mountain, butterfly, baby, girl, tiger, can, train, squirrel, beaver, forest, plain, bowl, dinosaur, willow_tree, man, leopard, plate, bicycle, skyscraper, road, beetle, bed, chair, otter, rose, house, palm_tree, lamp, cloud, bear, tractor, table, lion, dolphin, mouse, ray, whale, pine_tree, sea, rabbit, snake, rocket, chimpanzee, bottle, orange, mushroom, possum, shark
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0582
Base model
facebook/vit-mae-base