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_0883)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 3e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 883 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9632 |
| Val Accuracy | 0.8904 |
| Test Accuracy | 0.8870 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rocket, house, beaver, whale, willow_tree, caterpillar, maple_tree, clock, squirrel, sea, telephone, mushroom, dolphin, streetcar, fox, cattle, beetle, cloud, orchid, skunk, bus, trout, castle, tractor, lion, poppy, sunflower, motorcycle, elephant, pear, butterfly, porcupine, shrew, wardrobe, snail, bowl, tank, wolf, aquarium_fish, apple, seal, bee, lizard, lawn_mower, spider, dinosaur, bicycle, television, leopard, forest