Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0685)
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 | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 685 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9835 |
| Val Accuracy | 0.8955 |
| Test Accuracy | 0.8948 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
otter, aquarium_fish, bicycle, boy, shrew, apple, tractor, wardrobe, road, television, cup, motorcycle, lawn_mower, chair, dinosaur, lizard, orange, can, tank, trout, bowl, bus, man, cattle, possum, train, beaver, rocket, bed, worm, flatfish, seal, rabbit, tiger, cockroach, chimpanzee, sweet_pepper, couch, kangaroo, table, turtle, butterfly, plain, sunflower, elephant, poppy, bear, forest, willow_tree, porcupine
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0685
Base model
facebook/vit-mae-base