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_0597)
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 | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 597 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9910 |
| Val Accuracy | 0.8952 |
| Test Accuracy | 0.8898 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, orange, cup, poppy, butterfly, rose, cattle, seal, forest, lizard, clock, crab, shrew, pine_tree, orchid, lobster, palm_tree, leopard, house, motorcycle, worm, tank, apple, girl, wardrobe, turtle, can, sunflower, baby, porcupine, crocodile, bear, boy, pickup_truck, tractor, rabbit, keyboard, bus, beetle, ray, cloud, wolf, mouse, aquarium_fish, trout, skunk, squirrel, possum, chair, otter