Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0022)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 22 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9870 |
| Val Accuracy | 0.8947 |
| Test Accuracy | 0.8880 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
seal, snail, aquarium_fish, lizard, cattle, butterfly, shark, hamster, ray, possum, pine_tree, pear, orchid, wolf, beaver, apple, spider, squirrel, flatfish, dolphin, dinosaur, house, fox, chimpanzee, snake, otter, tractor, mouse, rocket, orange, leopard, boy, can, television, clock, train, pickup_truck, table, rose, cup, rabbit, whale, plain, porcupine, elephant, lobster, man, bed, caterpillar, palm_tree
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0022
Base model
facebook/vit-mae-base