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_0428)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 428 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5629 |
| Val Accuracy | 0.4592 |
| Test Accuracy | 0.4856 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
boy, pine_tree, telephone, cattle, couch, mouse, dinosaur, kangaroo, wolf, beaver, bee, table, bear, snail, crab, lizard, flatfish, ray, hamster, orange, dolphin, road, rose, pear, camel, bottle, elephant, crocodile, bus, skunk, rabbit, palm_tree, caterpillar, man, shark, motorcycle, apple, girl, oak_tree, lobster, forest, bed, maple_tree, aquarium_fish, bicycle, plain, skyscraper, cup, poppy, bridge