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_0594)
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 | 0.009 |
| Seed | 594 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5341 |
| Val Accuracy | 0.4403 |
| Test Accuracy | 0.4504 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, train, can, tiger, lamp, tulip, snake, bowl, cloud, crocodile, butterfly, girl, caterpillar, whale, mouse, oak_tree, palm_tree, sea, raccoon, plate, turtle, worm, clock, squirrel, man, cattle, possum, camel, castle, keyboard, rose, pine_tree, cup, crab, orange, apple, wolf, tank, bed, snail, woman, boy, seal, spider, fox, kangaroo, sweet_pepper, bridge, road, chair