Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0960)
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 |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 960 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9996 |
| Val Accuracy | 0.8947 |
| Test Accuracy | 0.8836 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, bowl, lion, couch, keyboard, tulip, raccoon, mouse, tank, oak_tree, girl, dolphin, rose, lamp, streetcar, wardrobe, sunflower, sweet_pepper, cockroach, cup, lawn_mower, lizard, willow_tree, motorcycle, clock, flatfish, skyscraper, mountain, tiger, bridge, snake, otter, boy, mushroom, maple_tree, dinosaur, bear, fox, chimpanzee, hamster, tractor, shrew, crocodile, seal, spider, wolf, telephone, skunk, shark, porcupine
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0960
Base model
facebook/vit-mae-base