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_0785)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 785 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8562 |
| Val Accuracy | 0.8083 |
| Test Accuracy | 0.8024 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, shrew, boy, otter, girl, poppy, ray, bear, couch, snail, squirrel, woman, house, plain, sweet_pepper, forest, elephant, chair, dolphin, spider, lawn_mower, tractor, bottle, pickup_truck, tiger, skyscraper, baby, lion, hamster, lizard, mountain, sunflower, possum, lamp, rose, butterfly, wolf, turtle, cattle, snake, lobster, apple, train, tulip, fox, pear, bee, orchid, leopard, bed