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_0635)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 635 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9326 |
| Val Accuracy | 0.8432 |
| Test Accuracy | 0.8574 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chimpanzee, girl, otter, turtle, lizard, castle, palm_tree, beetle, rose, flatfish, baby, motorcycle, pickup_truck, cattle, orchid, maple_tree, apple, worm, ray, bottle, forest, hamster, wardrobe, road, snake, fox, kangaroo, plate, caterpillar, skyscraper, tractor, wolf, mountain, cockroach, streetcar, butterfly, rocket, seal, lawn_mower, pear, train, bicycle, clock, cloud, beaver, mouse, shark, orange, boy, bed