Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0548)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 548 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9852 |
| Val Accuracy | 0.8507 |
| Test Accuracy | 0.8458 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, bus, snake, tractor, bee, squirrel, sea, maple_tree, apple, shrew, flatfish, rabbit, poppy, porcupine, train, woman, lawn_mower, spider, mountain, chimpanzee, shark, castle, leopard, road, can, rocket, baby, seal, snail, bear, turtle, girl, pickup_truck, camel, boy, worm, skunk, tank, streetcar, wolf, whale, crocodile, ray, bed, cattle, wardrobe, willow_tree, cockroach, sunflower, mouse
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0548
Base model
facebook/vit-mae-base