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_0771)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 771 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9948 |
| Val Accuracy | 0.8941 |
| Test Accuracy | 0.8926 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cup, bicycle, maple_tree, table, skyscraper, motorcycle, bee, house, porcupine, dinosaur, dolphin, bottle, lamp, crocodile, skunk, mountain, lobster, bus, spider, castle, streetcar, plate, beetle, bridge, telephone, woman, train, otter, palm_tree, kangaroo, cockroach, lion, apple, sea, orchid, couch, baby, bowl, willow_tree, flatfish, chimpanzee, whale, mouse, raccoon, turtle, sunflower, leopard, seal, oak_tree, pear