Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0621)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 621 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9972 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8904 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, kangaroo, plain, clock, snake, motorcycle, fox, telephone, porcupine, rose, aquarium_fish, tractor, mouse, poppy, television, whale, orange, squirrel, apple, tulip, willow_tree, pickup_truck, caterpillar, spider, lion, shark, seal, chair, bee, bear, snail, flatfish, table, mountain, baby, bowl, woman, trout, dinosaur, forest, rocket, raccoon, keyboard, bus, possum, pear, wolf, chimpanzee, couch, leopard
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0621
Base model
facebook/vit-mae-base