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_0736)
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 | 7e-05 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 736 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9307 |
| Val Accuracy | 0.8661 |
| Test Accuracy | 0.8738 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, sunflower, wardrobe, lobster, table, maple_tree, orchid, lawn_mower, bridge, elephant, apple, can, cockroach, sea, rose, mushroom, crab, skyscraper, kangaroo, flatfish, cloud, bee, bed, dinosaur, trout, porcupine, ray, otter, streetcar, bear, keyboard, fox, bus, hamster, plate, poppy, leopard, dolphin, chair, raccoon, tulip, castle, caterpillar, forest, squirrel, clock, pine_tree, tractor, palm_tree, beetle