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_0433)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 433 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9844 |
| Val Accuracy | 0.8864 |
| Test Accuracy | 0.8872 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tiger, bicycle, lion, wolf, cockroach, bus, lawn_mower, lobster, wardrobe, elephant, bear, porcupine, whale, worm, bridge, chimpanzee, man, mouse, leopard, willow_tree, hamster, oak_tree, crocodile, bed, rabbit, palm_tree, fox, flatfish, train, couch, orchid, streetcar, girl, seal, can, turtle, house, woman, camel, mountain, baby, forest, television, bee, ray, castle, tulip, motorcycle, skyscraper, lamp