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_0210)
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 210 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9800 |
| Val Accuracy | 0.8771 |
| Test Accuracy | 0.8814 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, snail, bed, bottle, rose, orchid, skunk, trout, caterpillar, woman, forest, baby, bowl, snake, willow_tree, worm, telephone, house, girl, flatfish, tank, elephant, poppy, mushroom, spider, train, bicycle, bus, squirrel, keyboard, porcupine, lawn_mower, rocket, beaver, motorcycle, pine_tree, can, fox, sweet_pepper, seal, sea, skyscraper, road, whale, wardrobe, cockroach, tractor, sunflower, plain, cup