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_0209)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 209 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9990 |
| Val Accuracy | 0.8973 |
| Test Accuracy | 0.8982 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, squirrel, man, boy, bed, orchid, tiger, lizard, castle, skunk, sunflower, trout, fox, rose, maple_tree, couch, wardrobe, bottle, pine_tree, dinosaur, shrew, chimpanzee, crab, pear, tractor, mushroom, cockroach, baby, elephant, beaver, whale, camel, spider, leopard, wolf, crocodile, bear, lion, forest, can, tulip, hamster, chair, seal, road, possum, beetle, caterpillar, sea, snail