Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0456)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 456 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9722 |
| Val Accuracy | 0.6048 |
| Test Accuracy | 0.6000 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crab, otter, can, shark, cloud, castle, man, snake, pine_tree, apple, girl, lobster, lamp, crocodile, possum, elephant, poppy, mouse, chimpanzee, rabbit, pear, beetle, woman, whale, squirrel, bear, lawn_mower, table, cockroach, rose, road, motorcycle, caterpillar, bed, sunflower, mushroom, tulip, lizard, hamster, boy, dolphin, rocket, television, bridge, worm, keyboard, bottle, kangaroo, butterfly, sea
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0456
Base model
facebook/vit-mae-base