Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0100)
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 | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 100 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9795 |
| Val Accuracy | 0.9000 |
| Test Accuracy | 0.8854 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
flatfish, leopard, cup, fox, whale, tractor, house, snail, can, crab, chair, bowl, orange, hamster, snake, chimpanzee, otter, bicycle, castle, sunflower, bottle, rabbit, telephone, forest, girl, baby, shrew, lawn_mower, mouse, motorcycle, porcupine, road, skunk, pickup_truck, lobster, couch, wardrobe, man, plain, squirrel, pear, caterpillar, woman, tulip, keyboard, bus, table, skyscraper, seal, lizard
- Downloads last month
- 5
Model tree for ProbeX/Model-J__MAE__model_idx_0100
Base model
facebook/vit-mae-base