Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0383)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 383 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9916 |
| Val Accuracy | 0.8779 |
| Test Accuracy | 0.8910 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, lamp, television, couch, poppy, pine_tree, mountain, whale, forest, beaver, maple_tree, snake, telephone, chimpanzee, crab, pickup_truck, pear, cattle, tractor, flatfish, train, fox, girl, bridge, streetcar, butterfly, table, bottle, tulip, road, elephant, man, rose, shark, wardrobe, turtle, oak_tree, otter, clock, bee, motorcycle, willow_tree, woman, seal, rocket, tank, mouse, caterpillar, worm, keyboard
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0383
Base model
facebook/vit-mae-base