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_0733)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 733 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6579 |
| Val Accuracy | 0.5136 |
| Test Accuracy | 0.5190 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, can, bear, rose, squirrel, clock, pickup_truck, keyboard, bus, bicycle, tank, house, lobster, bed, palm_tree, bowl, boy, girl, road, pear, television, telephone, mouse, turtle, lizard, cloud, pine_tree, couch, poppy, mountain, cup, snake, butterfly, dinosaur, plate, table, leopard, caterpillar, bee, camel, motorcycle, chimpanzee, plain, tiger, rocket, lion, raccoon, possum, cattle, maple_tree