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_0603)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 603 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9796 |
| Val Accuracy | 0.5443 |
| Test Accuracy | 0.5520 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, worm, pickup_truck, whale, boy, castle, bicycle, bee, bridge, rocket, beaver, tank, lion, shark, butterfly, poppy, porcupine, camel, rabbit, chair, raccoon, lizard, fox, cup, possum, plate, tulip, lawn_mower, willow_tree, beetle, tiger, train, snake, chimpanzee, flatfish, plain, girl, sunflower, spider, kangaroo, bed, woman, pear, crocodile, sweet_pepper, keyboard, mushroom, seal, apple, rose