Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0628)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 628 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9992 |
| Val Accuracy | 0.8923 |
| Test Accuracy | 0.8904 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, lamp, bowl, man, caterpillar, hamster, palm_tree, oak_tree, forest, poppy, aquarium_fish, butterfly, ray, lion, tank, couch, table, sunflower, keyboard, bed, spider, possum, crocodile, squirrel, willow_tree, fox, orange, whale, crab, beetle, raccoon, wolf, bicycle, television, bridge, clock, trout, shark, maple_tree, rocket, mouse, seal, rose, plain, chimpanzee, dolphin, snail, snake, cockroach, tractor
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0628
Base model
facebook/vit-mae-base