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_0654)
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 | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 654 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6079 |
| Val Accuracy | 0.5237 |
| Test Accuracy | 0.5362 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, house, aquarium_fish, motorcycle, pear, cloud, trout, orange, whale, television, bridge, oak_tree, palm_tree, wardrobe, mouse, shark, beetle, orchid, mushroom, tank, rabbit, lizard, train, snake, worm, sweet_pepper, bowl, sunflower, bed, sea, tiger, cattle, willow_tree, bicycle, girl, hamster, telephone, cup, snail, otter, castle, man, bee, shrew, bottle, possum, lion, elephant, squirrel, can