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_0394)
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 |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 394 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9888 |
| Val Accuracy | 0.8872 |
| Test Accuracy | 0.8858 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, crab, motorcycle, lizard, ray, crocodile, man, television, hamster, flatfish, bowl, skunk, rose, oak_tree, pickup_truck, orchid, tractor, squirrel, butterfly, worm, beaver, lamp, trout, kangaroo, train, lobster, maple_tree, mountain, pear, wolf, apple, clock, tiger, road, mouse, poppy, castle, shrew, chair, sunflower, streetcar, pine_tree, cloud, caterpillar, elephant, couch, whale, table, snail, bed