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_0913)
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 |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 913 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9440 |
| Val Accuracy | 0.8699 |
| Test Accuracy | 0.8752 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, lawn_mower, orange, castle, plain, fox, bowl, wardrobe, baby, bus, lamp, camel, chimpanzee, table, television, oak_tree, squirrel, telephone, pickup_truck, cockroach, sea, tank, palm_tree, elephant, beaver, bear, boy, trout, worm, snake, spider, plate, girl, rabbit, aquarium_fish, bee, pine_tree, rose, cloud, pear, leopard, dinosaur, whale, caterpillar, seal, motorcycle, beetle, flatfish, train, bridge