Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0076)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 76 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 1.0000 |
| Val Accuracy | 0.9003 |
| Test Accuracy | 0.9018 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, lizard, cloud, sunflower, palm_tree, spider, pine_tree, cockroach, mouse, apple, man, caterpillar, snake, plate, whale, rabbit, keyboard, worm, pickup_truck, skunk, tank, tiger, orange, porcupine, crab, plain, fox, woman, bee, raccoon, wolf, poppy, leopard, bridge, bottle, telephone, bus, possum, beetle, kangaroo, aquarium_fish, willow_tree, camel, couch, beaver, ray, clock, table, can, bicycle
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0076
Base model
facebook/vit-mae-base