Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0554)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 554 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9813 |
| Val Accuracy | 0.8840 |
| Test Accuracy | 0.8822 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, bowl, sweet_pepper, telephone, crocodile, chair, possum, road, sea, turtle, lion, chimpanzee, forest, pear, rocket, apple, porcupine, sunflower, tulip, tiger, pickup_truck, mushroom, streetcar, mountain, bee, whale, bear, fox, trout, tank, bridge, cloud, lawn_mower, boy, plate, bottle, hamster, couch, lamp, television, raccoon, table, girl, keyboard, poppy, lizard, wardrobe, castle, wolf, rose
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0554
Base model
facebook/vit-mae-base