Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0525)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 525 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9655 |
| Val Accuracy | 0.8728 |
| Test Accuracy | 0.8692 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, mushroom, bottle, camel, turtle, road, fox, wolf, baby, castle, cloud, dolphin, boy, house, shark, lamp, woman, keyboard, clock, skyscraper, aquarium_fish, elephant, trout, cattle, orchid, hamster, rabbit, pear, tank, pickup_truck, sweet_pepper, bed, table, maple_tree, palm_tree, tulip, dinosaur, flatfish, snail, sunflower, mountain, spider, cup, couch, television, streetcar, caterpillar, rose, skunk, apple
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0525
Base model
facebook/vit-mae-base