Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0176)
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 | 7e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 176 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9520 |
| Val Accuracy | 0.8632 |
| Test Accuracy | 0.8518 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, dinosaur, seal, telephone, oak_tree, orchid, mushroom, clock, pickup_truck, cockroach, ray, camel, spider, maple_tree, television, sweet_pepper, house, train, squirrel, sea, skyscraper, tiger, snake, tank, girl, porcupine, otter, lamp, turtle, rocket, streetcar, mountain, sunflower, chimpanzee, bridge, rose, cup, bowl, cattle, leopard, tractor, bus, whale, dolphin, tulip, table, plate, cloud, skunk, palm_tree
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0176
Base model
facebook/vit-mae-base