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_0227)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 227 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9679 |
| Val Accuracy | 0.6157 |
| Test Accuracy | 0.6256 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, sea, mountain, butterfly, plate, mushroom, bottle, fox, rocket, telephone, plain, crocodile, willow_tree, caterpillar, house, lamp, tiger, girl, pickup_truck, hamster, rose, leopard, streetcar, turtle, bed, motorcycle, aquarium_fish, bridge, boy, apple, table, can, beetle, orchid, cattle, ray, squirrel, porcupine, keyboard, sweet_pepper, lawn_mower, spider, tractor, pine_tree, road, bus, maple_tree, bowl, lizard, seal