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_0288)
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 | 0.0001 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 288 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9583 |
| Val Accuracy | 0.8739 |
| Test Accuracy | 0.8784 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, streetcar, turtle, forest, maple_tree, woman, telephone, sunflower, bear, pear, fox, ray, crab, bed, keyboard, worm, crocodile, dolphin, cattle, tulip, tank, tractor, plate, otter, mushroom, girl, road, mouse, cockroach, dinosaur, castle, elephant, camel, spider, willow_tree, hamster, beetle, chimpanzee, clock, orchid, lobster, cloud, pine_tree, apple, shrew, house, television, bottle, whale, cup