Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0933)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 933 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9914 |
| Val Accuracy | 0.9011 |
| Test Accuracy | 0.8980 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, mouse, fox, beetle, elephant, couch, baby, woman, orange, leopard, bottle, beaver, snake, dinosaur, rabbit, cattle, tank, kangaroo, lion, plate, cloud, tractor, keyboard, orchid, caterpillar, crab, sweet_pepper, rocket, bee, bridge, road, flatfish, television, tiger, sea, sunflower, pine_tree, porcupine, streetcar, skyscraper, trout, crocodile, lawn_mower, willow_tree, pickup_truck, plain, poppy, bear, forest, tulip
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0933
Base model
facebook/vit-mae-base