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_0529)
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 | 5e-05 |
| LR Scheduler | linear |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 529 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9985 |
| Val Accuracy | 0.9048 |
| Test Accuracy | 0.9032 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
motorcycle, woman, crab, mountain, rose, willow_tree, seal, telephone, cockroach, rocket, bridge, can, elephant, maple_tree, shark, spider, bowl, chimpanzee, streetcar, bus, tank, ray, sea, mouse, cloud, rabbit, tiger, caterpillar, lamp, bed, forest, lizard, lawn_mower, orange, hamster, road, fox, bear, pear, poppy, couch, castle, pine_tree, sunflower, leopard, dinosaur, raccoon, wolf, skunk, sweet_pepper