Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0499)
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_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 499 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9984 |
| Val Accuracy | 0.8904 |
| Test Accuracy | 0.8768 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
maple_tree, couch, fox, chimpanzee, plain, porcupine, turtle, beetle, bicycle, dinosaur, kangaroo, tank, tiger, orchid, house, cattle, chair, telephone, man, lawn_mower, worm, pickup_truck, motorcycle, snake, squirrel, girl, crocodile, boy, willow_tree, tractor, can, mouse, bridge, elephant, plate, pear, whale, camel, skunk, cup, shrew, tulip, baby, skyscraper, beaver, shark, bed, leopard, table, poppy
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0499
Base model
facebook/vit-mae-base