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_0284)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 284 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9952 |
| Val Accuracy | 0.8883 |
| Test Accuracy | 0.8876 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bridge, motorcycle, baby, pine_tree, otter, turtle, skyscraper, plain, streetcar, flatfish, cloud, forest, lawn_mower, woman, table, seal, rabbit, rocket, mushroom, oak_tree, road, possum, dinosaur, wolf, caterpillar, whale, poppy, bed, raccoon, boy, wardrobe, fox, pickup_truck, maple_tree, ray, bear, chimpanzee, butterfly, bicycle, bottle, tank, palm_tree, orchid, trout, leopard, shrew, man, castle, shark, lizard