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_0085)
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 | 0.0003 |
| LR Scheduler | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 85 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9382 |
| Val Accuracy | 0.6088 |
| Test Accuracy | 0.6080 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bowl, camel, dolphin, keyboard, porcupine, mouse, rocket, streetcar, hamster, crocodile, sunflower, shark, mushroom, skyscraper, can, leopard, bed, wolf, train, palm_tree, snail, possum, cattle, bottle, ray, cloud, sea, kangaroo, boy, lion, bridge, castle, tiger, fox, bicycle, man, wardrobe, crab, turtle, beaver, whale, bus, lawn_mower, squirrel, mountain, skunk, lobster, chimpanzee, table, bear