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_0407)
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 | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 407 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9847 |
| Val Accuracy | 0.8880 |
| Test Accuracy | 0.8964 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, flatfish, dinosaur, bee, house, fox, shrew, beetle, crocodile, woman, poppy, television, bottle, road, wolf, bear, hamster, squirrel, apple, lion, rocket, pine_tree, pear, bridge, orange, tiger, telephone, chimpanzee, willow_tree, caterpillar, man, seal, dolphin, baby, couch, spider, beaver, forest, cup, raccoon, snake, rose, trout, mouse, aquarium_fish, cattle, chair, camel, mushroom, tulip