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_0995)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 995 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9776 |
| Val Accuracy | 0.8827 |
| Test Accuracy | 0.8944 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, pickup_truck, girl, keyboard, wolf, beetle, trout, chimpanzee, crocodile, sweet_pepper, mountain, orchid, lizard, woman, cup, table, can, spider, worm, butterfly, snake, bicycle, kangaroo, caterpillar, oak_tree, plate, aquarium_fish, television, crab, baby, tractor, tulip, bowl, tank, boy, bear, mushroom, sunflower, forest, camel, lobster, pear, raccoon, bottle, possum, shark, poppy, motorcycle, cloud, whale