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_0400)
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 | 5e-05 |
| LR Scheduler | constant |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 400 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9068 |
| Val Accuracy | 0.8464 |
| Test Accuracy | 0.8360 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
apple, caterpillar, ray, wardrobe, cattle, tiger, raccoon, chair, porcupine, lawn_mower, possum, telephone, motorcycle, lobster, whale, flatfish, worm, chimpanzee, kangaroo, train, girl, lizard, hamster, table, snake, crocodile, dinosaur, palm_tree, beetle, tank, crab, pine_tree, turtle, cup, butterfly, mountain, seal, plain, otter, lamp, dolphin, skyscraper, house, wolf, road, orchid, bicycle, camel, skunk, squirrel