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_0130)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 130 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9144 |
| Val Accuracy | 0.8483 |
| Test Accuracy | 0.8622 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, girl, orchid, baby, rocket, chimpanzee, woman, raccoon, crocodile, lawn_mower, mountain, apple, cloud, orange, bridge, bear, sea, camel, caterpillar, castle, bowl, plate, butterfly, tiger, willow_tree, palm_tree, man, trout, bee, worm, shark, cockroach, shrew, cattle, flatfish, mouse, television, road, dinosaur, boy, chair, fox, wolf, bottle, kangaroo, tulip, elephant, motorcycle, aquarium_fish, porcupine