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_0729)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 729 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9972 |
| Val Accuracy | 0.8936 |
| Test Accuracy | 0.8904 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
baby, bowl, man, castle, porcupine, bridge, leopard, pear, willow_tree, train, forest, camel, sea, bed, worm, turtle, snail, streetcar, sunflower, girl, lion, squirrel, tractor, trout, road, pine_tree, raccoon, orchid, wolf, couch, cloud, poppy, possum, boy, skunk, pickup_truck, snake, bus, can, lamp, butterfly, tiger, oak_tree, aquarium_fish, cup, caterpillar, seal, orange, motorcycle, shark