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_0408)
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 | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 408 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9324 |
| Val Accuracy | 0.8507 |
| Test Accuracy | 0.8544 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, shark, beaver, skunk, road, boy, rocket, tulip, rose, motorcycle, spider, lion, train, pickup_truck, willow_tree, bus, bear, wardrobe, seal, pine_tree, crocodile, aquarium_fish, dinosaur, lamp, table, baby, mouse, bee, skyscraper, woman, raccoon, cockroach, bicycle, dolphin, sweet_pepper, porcupine, castle, snail, cup, wolf, oak_tree, hamster, kangaroo, maple_tree, can, plain, apple, palm_tree, ray, cloud