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_0334)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 334 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9434 |
| Val Accuracy | 0.8552 |
| Test Accuracy | 0.8554 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pickup_truck, road, maple_tree, cloud, tulip, kangaroo, crab, tiger, motorcycle, castle, willow_tree, bridge, woman, rose, forest, tractor, keyboard, trout, lobster, girl, bed, wolf, house, couch, aquarium_fish, sweet_pepper, beetle, boy, squirrel, butterfly, television, pear, orchid, leopard, rabbit, snail, lawn_mower, dolphin, raccoon, worm, beaver, chair, telephone, plain, wardrobe, fox, spider, pine_tree, caterpillar, skyscraper