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_0454)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 454 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8767 |
| Val Accuracy | 0.8365 |
| Test Accuracy | 0.8394 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, tractor, leopard, hamster, tank, can, castle, crocodile, road, camel, elephant, bowl, chimpanzee, possum, apple, man, aquarium_fish, cloud, beetle, snail, mushroom, dinosaur, boy, mouse, lawn_mower, lizard, kangaroo, sunflower, couch, chair, girl, tiger, oak_tree, mountain, cup, bicycle, whale, beaver, bottle, dolphin, train, ray, spider, shrew, pickup_truck, otter, squirrel, butterfly, orange, plain