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_0924)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 924 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9971 |
| Val Accuracy | 0.8923 |
| Test Accuracy | 0.8938 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, pine_tree, snail, bear, elephant, house, bee, lobster, shark, otter, rocket, rabbit, orange, baby, porcupine, telephone, lizard, shrew, tulip, skunk, snake, cockroach, streetcar, kangaroo, ray, girl, squirrel, aquarium_fish, turtle, can, whale, spider, apple, plain, rose, oak_tree, orchid, fox, keyboard, bowl, television, wardrobe, caterpillar, boy, trout, camel, crocodile, castle, leopard, couch