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_0717)
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 | 0.0005 |
| LR Scheduler | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 717 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6872 |
| Val Accuracy | 0.5256 |
| Test Accuracy | 0.5210 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, house, plain, bicycle, skyscraper, orange, girl, motorcycle, squirrel, forest, man, flatfish, palm_tree, table, bear, cup, pear, rocket, raccoon, bus, lizard, bridge, castle, seal, bowl, trout, bottle, clock, tulip, pickup_truck, rabbit, spider, mountain, whale, boy, plate, butterfly, telephone, train, mushroom, otter, beaver, camel, worm, tiger, cattle, woman, lamp, shark, maple_tree