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_0737)
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 | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 737 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9558 |
| Val Accuracy | 0.8507 |
| Test Accuracy | 0.8492 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
crocodile, leopard, mountain, girl, snake, bus, woman, aquarium_fish, pear, cattle, skunk, can, house, tiger, wardrobe, bear, lobster, keyboard, possum, motorcycle, beetle, man, lawn_mower, couch, elephant, cloud, lizard, rocket, caterpillar, tank, worm, orchid, chair, camel, plain, table, mouse, butterfly, fox, telephone, cup, castle, bee, forest, flatfish, ray, hamster, beaver, tractor, pickup_truck