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_0179)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 179 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5999 |
| Val Accuracy | 0.5323 |
| Test Accuracy | 0.5452 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
castle, spider, mouse, table, bear, house, butterfly, fox, lobster, tank, apple, dinosaur, palm_tree, pear, lizard, crab, motorcycle, keyboard, flatfish, road, streetcar, bowl, ray, worm, rabbit, bottle, lamp, bicycle, turtle, sea, mushroom, bee, leopard, shrew, plain, lawn_mower, mountain, chair, tulip, rocket, wolf, snail, seal, pickup_truck, maple_tree, telephone, poppy, squirrel, rose, train