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_0531)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 531 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8944 |
| Val Accuracy | 0.8328 |
| Test Accuracy | 0.8354 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, maple_tree, woman, cloud, bottle, streetcar, poppy, lizard, kangaroo, snail, plate, motorcycle, crocodile, oak_tree, pickup_truck, shrew, skyscraper, train, pine_tree, baby, beetle, tractor, rabbit, tulip, cup, squirrel, lamp, tank, elephant, bowl, snake, skunk, raccoon, fox, castle, keyboard, mushroom, couch, mountain, boy, willow_tree, pear, man, orchid, rose, camel, porcupine, house, bus, dinosaur