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_0449)
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 | linear |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 449 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9906 |
| Val Accuracy | 0.9099 |
| Test Accuracy | 0.9090 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
road, chimpanzee, bridge, possum, trout, lion, dinosaur, apple, wolf, tulip, hamster, television, willow_tree, lawn_mower, crocodile, porcupine, palm_tree, man, beetle, fox, cattle, aquarium_fish, wardrobe, mouse, cockroach, train, tank, rose, bear, dolphin, pine_tree, snake, boy, snail, skunk, cup, sweet_pepper, bottle, shark, motorcycle, sunflower, girl, caterpillar, pickup_truck, sea, seal, butterfly, turtle, lamp, skyscraper