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_0057)
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 | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 57 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9756 |
| Val Accuracy | 0.8832 |
| Test Accuracy | 0.8882 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cloud, fox, bee, skunk, crocodile, camel, tractor, house, dinosaur, rose, wardrobe, woman, squirrel, shrew, lion, apple, oak_tree, streetcar, bed, elephant, crab, rabbit, orange, tiger, mountain, kangaroo, plate, snake, shark, bear, pine_tree, bowl, spider, can, beetle, bicycle, poppy, otter, clock, pear, forest, chimpanzee, motorcycle, orchid, road, palm_tree, skyscraper, pickup_truck, cockroach, caterpillar