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_0450)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 450 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9777 |
| Val Accuracy | 0.8824 |
| Test Accuracy | 0.8824 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, couch, lobster, train, pine_tree, baby, raccoon, clock, lion, poppy, caterpillar, cattle, palm_tree, bowl, bottle, rocket, willow_tree, rose, bicycle, house, skunk, sweet_pepper, streetcar, dolphin, bus, beetle, apple, flatfish, cockroach, skyscraper, kangaroo, mushroom, plain, aquarium_fish, lamp, orchid, tractor, camel, forest, squirrel, whale, mouse, crocodile, pear, man, sunflower, tiger, oak_tree, castle, beaver