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_0917)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 917 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9953 |
| Val Accuracy | 0.8840 |
| Test Accuracy | 0.8872 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, pickup_truck, spider, worm, wolf, girl, palm_tree, plain, road, rose, bowl, television, telephone, lizard, pine_tree, chimpanzee, squirrel, pear, sunflower, lobster, caterpillar, snail, tractor, kangaroo, baby, dinosaur, willow_tree, cockroach, turtle, whale, skunk, butterfly, raccoon, elephant, clock, mushroom, porcupine, orchid, mouse, chair, house, cattle, rocket, bear, cloud, possum, otter, bed, beaver, mountain