Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0555)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 555 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9699 |
| Val Accuracy | 0.8517 |
| Test Accuracy | 0.8624 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mushroom, bus, poppy, table, flatfish, rose, hamster, beetle, can, rocket, girl, sea, bed, willow_tree, chair, wardrobe, pickup_truck, oak_tree, seal, mountain, woman, bicycle, crocodile, aquarium_fish, shark, castle, porcupine, butterfly, lamp, worm, forest, palm_tree, cup, tank, otter, lobster, road, baby, skunk, sunflower, crab, bowl, raccoon, snake, mouse, cockroach, tulip, keyboard, bear, skyscraper
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0555
Base model
facebook/vit-mae-base