Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0138)
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 138 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9882 |
| Val Accuracy | 0.8541 |
| Test Accuracy | 0.8578 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, pear, house, squirrel, train, woman, couch, spider, turtle, fox, skyscraper, bus, tractor, plain, apple, whale, dolphin, boy, tiger, bed, mushroom, trout, dinosaur, flatfish, tulip, rose, orchid, wolf, lawn_mower, chimpanzee, poppy, road, rabbit, cockroach, baby, bowl, chair, mouse, keyboard, oak_tree, telephone, sweet_pepper, can, forest, rocket, otter, bear, sunflower, kangaroo, castle
- Downloads last month
- 2
Model tree for ProbeX/Model-J__MAE__model_idx_0138
Base model
facebook/vit-mae-base