Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0942)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 942 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9202 |
| Val Accuracy | 0.7989 |
| Test Accuracy | 0.8020 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, road, rocket, cockroach, caterpillar, baby, bowl, tulip, telephone, tank, maple_tree, apple, aquarium_fish, sunflower, crocodile, snake, table, cloud, porcupine, crab, otter, tractor, elephant, butterfly, plain, orange, train, rose, bear, leopard, bicycle, chimpanzee, television, woman, pickup_truck, chair, squirrel, skunk, wardrobe, motorcycle, ray, palm_tree, snail, seal, sweet_pepper, bottle, sea, man, girl, skyscraper
- Downloads last month
- 6
Model tree for ProbeX/Model-J__MAE__model_idx_0942
Base model
facebook/vit-mae-base