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_0065)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 65 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9365 |
| Val Accuracy | 0.8765 |
| Test Accuracy | 0.8794 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
butterfly, tank, caterpillar, orchid, crab, mountain, willow_tree, rocket, aquarium_fish, skyscraper, bus, girl, elephant, keyboard, telephone, crocodile, pear, snake, rabbit, beetle, sweet_pepper, lawn_mower, cloud, bottle, pine_tree, television, oak_tree, man, tulip, spider, cockroach, bear, shark, baby, dolphin, turtle, tractor, porcupine, seal, snail, bicycle, clock, apple, beaver, whale, raccoon, dinosaur, train, road, sunflower