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_0867)
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 | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 867 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9803 |
| Val Accuracy | 0.8795 |
| Test Accuracy | 0.8826 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
fox, skyscraper, porcupine, bed, chair, dolphin, sunflower, train, oak_tree, turtle, boy, bottle, girl, rabbit, man, cattle, wolf, sea, maple_tree, ray, elephant, bear, orchid, bowl, trout, lobster, can, bee, lion, spider, beaver, hamster, house, road, bicycle, crab, snail, otter, lizard, mouse, beetle, baby, apple, tiger, clock, table, possum, caterpillar, cloud, snake