Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0264)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 264 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.8595 |
| Test Accuracy | 0.8606 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, trout, clock, castle, apple, tiger, leopard, orange, hamster, lobster, tractor, lamp, flatfish, cloud, elephant, man, bridge, tank, seal, shrew, train, chimpanzee, cockroach, ray, camel, cup, can, lawn_mower, pine_tree, porcupine, dolphin, crocodile, bicycle, keyboard, lion, dinosaur, mouse, boy, forest, butterfly, plate, snail, orchid, chair, otter, oak_tree, maple_tree, mountain, motorcycle, squirrel
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0264
Base model
facebook/vit-mae-base