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_0776)
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 | 0.0003 |
| LR Scheduler | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 776 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9998 |
| Val Accuracy | 0.8392 |
| Test Accuracy | 0.8452 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, bottle, pine_tree, lawn_mower, fox, wardrobe, snail, bed, beaver, worm, snake, whale, caterpillar, boy, cattle, bridge, sweet_pepper, cup, orchid, willow_tree, shrew, baby, hamster, kangaroo, pear, dinosaur, apple, spider, chimpanzee, shark, porcupine, bowl, mountain, wolf, lion, orange, tractor, television, tulip, trout, leopard, bear, plain, lamp, poppy, man, squirrel, lobster, crab, oak_tree