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_0021)
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 | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 21 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9906 |
| Val Accuracy | 0.8925 |
| Test Accuracy | 0.8998 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, motorcycle, woman, bowl, forest, lamp, bicycle, lizard, mouse, rose, chair, man, crab, bus, pine_tree, tiger, boy, beetle, snake, sweet_pepper, poppy, streetcar, willow_tree, tank, cattle, sea, pickup_truck, otter, snail, trout, plate, road, raccoon, plain, skyscraper, crocodile, leopard, mountain, ray, elephant, squirrel, flatfish, house, skunk, clock, lawn_mower, couch, cup, bear, television