Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0489)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 489 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9802 |
| Val Accuracy | 0.8776 |
| Test Accuracy | 0.8866 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, house, palm_tree, forest, rabbit, can, plate, cockroach, sea, lobster, shrew, fox, motorcycle, beetle, butterfly, skunk, snake, bee, lizard, keyboard, bed, ray, sunflower, kangaroo, chimpanzee, whale, pear, willow_tree, crocodile, girl, seal, hamster, orchid, pickup_truck, plain, apple, orange, tiger, skyscraper, spider, poppy, otter, lawn_mower, raccoon, wolf, snail, train, road, tractor, man
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0489
Base model
facebook/vit-mae-base