Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0319)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 319 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9993 |
| Val Accuracy | 0.8904 |
| Test Accuracy | 0.8878 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, mushroom, bee, kangaroo, television, elephant, skyscraper, skunk, dinosaur, bridge, palm_tree, aquarium_fish, shark, otter, lawn_mower, sunflower, whale, worm, forest, hamster, orchid, plain, train, plate, boy, lobster, bowl, squirrel, turtle, trout, dolphin, lizard, rabbit, house, wolf, couch, girl, seal, cockroach, orange, lion, cloud, crab, chair, flatfish, baby, butterfly, pickup_truck, cattle, sweet_pepper
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0319
Base model
facebook/vit-mae-base