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_0038)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 38 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9997 |
| Val Accuracy | 0.8784 |
| Test Accuracy | 0.8728 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
girl, otter, porcupine, seal, turtle, television, plain, pine_tree, cattle, castle, possum, plate, baby, lawn_mower, lion, couch, bicycle, forest, cup, crab, lamp, maple_tree, keyboard, clock, worm, motorcycle, dolphin, leopard, palm_tree, squirrel, rose, beetle, oak_tree, shark, dinosaur, ray, pear, crocodile, man, tiger, can, road, cloud, mouse, bottle, bowl, orange, camel, snake, bridge