Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0473)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 473 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9373 |
| Val Accuracy | 0.8675 |
| Test Accuracy | 0.8578 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plate, fox, snake, bridge, caterpillar, raccoon, television, can, woman, elephant, mushroom, otter, baby, squirrel, tractor, cockroach, sweet_pepper, camel, aquarium_fish, rose, spider, wolf, ray, bed, castle, tulip, telephone, bear, rabbit, butterfly, flatfish, sunflower, dinosaur, bus, road, shark, willow_tree, porcupine, oak_tree, girl, pickup_truck, seal, crab, mountain, poppy, pear, skunk, possum, beetle, rocket
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0473
Base model
facebook/vit-mae-base