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_0431)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 431 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9964 |
| Val Accuracy | 0.8757 |
| Test Accuracy | 0.8880 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, bee, ray, orange, crab, rocket, apple, cattle, oak_tree, tiger, baby, train, cloud, snail, pine_tree, bed, lawn_mower, tractor, tulip, bicycle, pear, woman, possum, girl, rose, poppy, wolf, sweet_pepper, porcupine, cup, lion, otter, rabbit, kangaroo, flatfish, willow_tree, forest, hamster, shark, sea, wardrobe, bowl, boy, sunflower, lizard, dinosaur, chair, plain, man, keyboard