Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0568)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 568 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9740 |
| Val Accuracy | 0.8763 |
| Test Accuracy | 0.8758 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, squirrel, clock, baby, motorcycle, pickup_truck, cloud, sunflower, raccoon, wardrobe, pine_tree, cattle, whale, shark, lamp, rabbit, skunk, maple_tree, lobster, telephone, trout, snake, bridge, caterpillar, crocodile, rose, orchid, beetle, boy, bowl, sea, porcupine, cockroach, turtle, aquarium_fish, ray, orange, worm, man, keyboard, train, road, tiger, woman, sweet_pepper, crab, flatfish, wolf, dolphin, camel
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0568
Base model
facebook/vit-mae-base