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_0686)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 686 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9968 |
| Val Accuracy | 0.9029 |
| Test Accuracy | 0.9052 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
whale, train, squirrel, crab, tractor, bottle, ray, pear, camel, porcupine, turtle, plate, snake, bowl, woman, bridge, shark, elephant, can, beetle, streetcar, house, cattle, bee, dolphin, baby, mountain, bicycle, otter, oak_tree, palm_tree, pickup_truck, cockroach, television, pine_tree, lamp, butterfly, wolf, lobster, orange, cloud, apple, bed, plain, bear, caterpillar, telephone, tulip, leopard, man