metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0446)
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 | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 446 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9392 |
| Val Accuracy | 0.8704 |
| Test Accuracy | 0.8782 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, baby, lobster, pickup_truck, kangaroo, woman, clock, house, caterpillar, streetcar, bottle, aquarium_fish, fox, bridge, mountain, dolphin, shrew, castle, forest, keyboard, trout, camel, whale, crab, pear, bear, train, cattle, man, lion, bicycle, wardrobe, lawn_mower, pine_tree, road, mushroom, cockroach, hamster, cup, sweet_pepper, possum, skunk, palm_tree, mouse, rose, cloud, butterfly, squirrel, tiger, shark