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_0032)
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 | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 32 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4970 |
| Val Accuracy | 0.4485 |
| Test Accuracy | 0.4530 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wolf, bridge, road, couch, pear, turtle, crocodile, seal, bowl, bee, kangaroo, lizard, train, castle, lawn_mower, man, television, sunflower, sweet_pepper, tractor, snail, motorcycle, lion, aquarium_fish, possum, rocket, porcupine, bed, dolphin, shrew, shark, trout, telephone, bottle, dinosaur, fox, beetle, girl, maple_tree, apple, wardrobe, snake, ray, woman, poppy, tank, rabbit, whale, streetcar, lobster