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_0112)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 112 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9611 |
| Val Accuracy | 0.8691 |
| Test Accuracy | 0.8636 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, mouse, crab, pear, caterpillar, rose, cattle, willow_tree, motorcycle, streetcar, road, wolf, chimpanzee, maple_tree, butterfly, bottle, tiger, elephant, shark, bed, tulip, sweet_pepper, spider, beaver, cup, telephone, lobster, wardrobe, castle, shrew, crocodile, orchid, squirrel, lamp, bus, flatfish, keyboard, possum, man, dinosaur, plate, palm_tree, whale, raccoon, forest, lion, bee, poppy, train, rocket