Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0070)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 70 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9737 |
| Val Accuracy | 0.8755 |
| Test Accuracy | 0.8702 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bed, bottle, caterpillar, sea, snake, crocodile, rose, maple_tree, table, spider, fox, tank, kangaroo, boy, skunk, rabbit, streetcar, worm, raccoon, flatfish, snail, crab, plain, possum, orchid, trout, seal, baby, can, keyboard, man, tiger, motorcycle, turtle, aquarium_fish, shrew, cloud, wardrobe, mushroom, leopard, cockroach, pine_tree, pickup_truck, otter, wolf, orange, forest, sweet_pepper, bus, porcupine
- Downloads last month
- -
Model tree for ProbeX/Model-J__MAE__model_idx_0070
Base model
facebook/vit-mae-base