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_0248)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 248 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9955 |
| Val Accuracy | 0.9013 |
| Test Accuracy | 0.8974 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
caterpillar, sweet_pepper, ray, maple_tree, snake, leopard, tiger, shark, wardrobe, hamster, porcupine, baby, rose, orange, pine_tree, couch, pickup_truck, mushroom, seal, dinosaur, spider, possum, motorcycle, cattle, mouse, sea, train, crocodile, can, worm, skyscraper, lion, crab, plate, lizard, apple, sunflower, beetle, bicycle, man, road, house, castle, girl, snail, turtle, tulip, trout, bee, bear