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_0625)
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 | 3e-05 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 625 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9750 |
| Val Accuracy | 0.8640 |
| Test Accuracy | 0.8642 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
kangaroo, hamster, bus, rabbit, lawn_mower, fox, woman, oak_tree, girl, orange, keyboard, mountain, baby, lamp, crocodile, wardrobe, skyscraper, whale, lobster, couch, cockroach, train, flatfish, trout, willow_tree, maple_tree, bee, house, worm, possum, mouse, squirrel, chimpanzee, bottle, aquarium_fish, tiger, snail, bicycle, sweet_pepper, pine_tree, shark, ray, boy, road, otter, plain, bear, apple, tractor, wolf