Model-J MAE
Collection
1002 items • Updated
Model-J: MAE Model (model_idx_0792)
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 | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 792 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9056 |
| Val Accuracy | 0.8344 |
| Test Accuracy | 0.8390 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, can, cup, fox, beaver, forest, bed, pine_tree, lobster, pear, train, bridge, bowl, tractor, cattle, willow_tree, sunflower, elephant, sweet_pepper, clock, ray, tiger, crab, snail, oak_tree, mountain, road, pickup_truck, tulip, boy, cockroach, whale, motorcycle, raccoon, rocket, bottle, shrew, man, wolf, leopard, girl, skyscraper, wardrobe, baby, lizard, plain, poppy, table, lamp, orchid
- Downloads last month
- 1
Model tree for ProbeX/Model-J__MAE__model_idx_0792
Base model
facebook/vit-mae-base