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_0332)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | constant |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 332 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9883 |
| Val Accuracy | 0.8605 |
| Test Accuracy | 0.8570 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, lizard, butterfly, sunflower, fox, house, lawn_mower, wolf, squirrel, raccoon, pine_tree, oak_tree, tank, rose, cup, chimpanzee, telephone, tiger, bee, whale, forest, clock, flatfish, camel, porcupine, aquarium_fish, skunk, willow_tree, bed, elephant, hamster, ray, shark, woman, snake, orchid, spider, table, shrew, man, train, baby, orange, bridge, worm, boy, skyscraper, television, crocodile, road