Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0698)
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 | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 698 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9734 |
| Val Accuracy | 0.8555 |
| Test Accuracy | 0.8760 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, possum, seal, trout, tulip, mouse, road, maple_tree, beetle, chimpanzee, tiger, chair, ray, orange, porcupine, couch, wardrobe, beaver, snake, woman, girl, apple, bicycle, kangaroo, poppy, squirrel, bridge, snail, house, elephant, man, pear, clock, boy, plate, keyboard, baby, rose, pine_tree, sweet_pepper, shark, television, crab, mushroom, cloud, oak_tree, rabbit, caterpillar, lamp, lawn_mower
- Downloads last month
- 4
Model tree for ProbeX/Model-J__MAE__model_idx_0698
Base model
facebook/vit-mae-base