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_0950)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 950 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9240 |
| Val Accuracy | 0.8608 |
| Test Accuracy | 0.8714 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, rose, can, man, caterpillar, streetcar, wolf, sunflower, plain, forest, tank, cockroach, trout, camel, castle, bridge, lobster, road, orange, porcupine, house, spider, bear, beaver, lawn_mower, snail, boy, chair, mushroom, crab, wardrobe, seal, motorcycle, lizard, lion, willow_tree, cloud, girl, shark, pickup_truck, couch, whale, kangaroo, poppy, pear, dolphin, raccoon, woman, bowl, cup