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_0642)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 642 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8633 |
| Val Accuracy | 0.8035 |
| Test Accuracy | 0.8062 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, poppy, cloud, porcupine, lizard, motorcycle, tractor, wolf, shark, flatfish, snake, beaver, tank, wardrobe, plate, raccoon, mouse, can, ray, bicycle, bowl, lion, otter, possum, girl, pine_tree, hamster, skunk, train, telephone, orchid, road, oak_tree, apple, caterpillar, bed, woman, television, rocket, lobster, seal, bus, pickup_truck, kangaroo, streetcar, beetle, tulip, leopard, elephant, forest