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_0229)
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 | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 229 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9928 |
| Val Accuracy | 0.9032 |
| Test Accuracy | 0.8986 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cattle, worm, orchid, lawn_mower, television, motorcycle, camel, ray, castle, cockroach, oak_tree, rose, crocodile, fox, bowl, raccoon, couch, keyboard, palm_tree, squirrel, beetle, leopard, house, tiger, sunflower, bear, snake, plain, dinosaur, sea, rabbit, willow_tree, mouse, seal, man, skunk, pine_tree, rocket, lion, aquarium_fish, poppy, chair, chimpanzee, dolphin, turtle, telephone, flatfish, possum, caterpillar, tank