Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0851)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 851 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9851 |
| Val Accuracy | 0.8693 |
| Test Accuracy | 0.8610 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, dinosaur, hamster, clock, forest, ray, train, flatfish, plate, squirrel, mushroom, cup, maple_tree, beaver, willow_tree, bed, rabbit, lawn_mower, cloud, sea, orchid, woman, road, tulip, boy, apple, lion, lobster, man, tank, couch, cockroach, spider, bridge, turtle, skunk, girl, can, poppy, bus, snake, porcupine, aquarium_fish, wolf, baby, crocodile, wardrobe, camel, chimpanzee, raccoon
- Downloads last month
- 3
Model tree for ProbeX/Model-J__MAE__model_idx_0851
Base model
facebook/vit-mae-base