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_0641)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 641 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9971 |
| Val Accuracy | 0.8549 |
| Test Accuracy | 0.8582 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
turtle, wolf, lobster, rocket, forest, snake, beaver, sea, plain, house, couch, tank, worm, aquarium_fish, skyscraper, dinosaur, lamp, can, shrew, streetcar, orange, crocodile, apple, boy, poppy, otter, bowl, girl, mouse, shark, camel, man, chimpanzee, woman, motorcycle, sweet_pepper, palm_tree, cattle, pickup_truck, caterpillar, lion, snail, sunflower, baby, beetle, butterfly, porcupine, bear, whale, castle