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_0552)
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 | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 552 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5063 |
| Val Accuracy | 0.4413 |
| Test Accuracy | 0.4584 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, lion, possum, fox, rabbit, beaver, can, rocket, road, motorcycle, boy, squirrel, train, plate, bus, tractor, willow_tree, girl, spider, dolphin, raccoon, flatfish, tiger, otter, leopard, palm_tree, lizard, mushroom, skyscraper, television, sunflower, maple_tree, crab, skunk, poppy, sweet_pepper, pine_tree, tank, lawn_mower, worm, crocodile, lobster, pickup_truck, chimpanzee, telephone, orange, kangaroo, pear, trout, bear