Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0175)
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 | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 175 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9949 |
| Val Accuracy | 0.8955 |
| Test Accuracy | 0.8988 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, worm, bee, tulip, butterfly, dinosaur, bicycle, tiger, chair, porcupine, apple, bowl, seal, spider, bridge, telephone, chimpanzee, lamp, television, beaver, leopard, ray, whale, shark, train, tractor, turtle, lion, sea, palm_tree, possum, pickup_truck, maple_tree, mountain, baby, mushroom, mouse, snake, sunflower, squirrel, kangaroo, man, boy, skunk, willow_tree, fox, caterpillar, pear, wolf, can
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0175
Base model
facebook/vit-mae-base