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_0159)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 159 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9974 |
| Val Accuracy | 0.9037 |
| Test Accuracy | 0.9010 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, orange, table, plate, train, dinosaur, possum, bicycle, poppy, pear, cockroach, tank, plain, porcupine, sunflower, mushroom, shark, orchid, otter, beaver, boy, raccoon, skunk, oak_tree, bowl, forest, butterfly, lion, television, elephant, leopard, fox, seal, road, caterpillar, hamster, castle, aquarium_fish, cloud, cattle, trout, spider, snake, wardrobe, snail, chair, apple, kangaroo, shrew, lizard