Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0918)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 918 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9906 |
| Val Accuracy | 0.9120 |
| Test Accuracy | 0.8948 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lizard, chair, maple_tree, lobster, bottle, forest, flatfish, motorcycle, orange, rocket, can, tulip, squirrel, sea, lawn_mower, snake, man, tank, mountain, poppy, rabbit, rose, couch, hamster, turtle, pine_tree, butterfly, streetcar, train, chimpanzee, boy, shark, pear, plate, shrew, lamp, bridge, bicycle, baby, sweet_pepper, wardrobe, cloud, porcupine, road, mushroom, pickup_truck, otter, bee, cockroach, cup
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0918
Base model
facebook/vit-mae-base