Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0664)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 664 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9423 |
| Val Accuracy | 0.8741 |
| Test Accuracy | 0.8764 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
leopard, snake, cockroach, maple_tree, pine_tree, aquarium_fish, mushroom, crocodile, tank, plain, wolf, table, bicycle, sea, trout, mouse, pear, beetle, lobster, possum, pickup_truck, ray, orchid, kangaroo, palm_tree, crab, cattle, skunk, woman, camel, lamp, road, skyscraper, dolphin, butterfly, oak_tree, apple, baby, snail, whale, tulip, willow_tree, worm, wardrobe, plate, chair, bridge, fox, chimpanzee, otter
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0664
Base model
facebook/vit-mae-base