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_0265)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 265 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9866 |
| Val Accuracy | 0.9011 |
| Test Accuracy | 0.9082 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, mushroom, cup, lawn_mower, skyscraper, clock, worm, orchid, shrew, bowl, plain, dinosaur, chair, caterpillar, hamster, table, television, motorcycle, lion, lamp, can, train, raccoon, girl, forest, fox, pickup_truck, tank, otter, apple, boy, cloud, bed, wardrobe, castle, pear, skunk, mountain, whale, snake, tractor, beaver, rose, spider, chimpanzee, shark, wolf, cockroach, orange, palm_tree