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_0706)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 706 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9616 |
| Val Accuracy | 0.8504 |
| Test Accuracy | 0.8542 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
man, squirrel, porcupine, leopard, pear, sea, snake, elephant, dolphin, streetcar, skyscraper, table, house, clock, wardrobe, cockroach, whale, castle, trout, pine_tree, boy, crocodile, mushroom, rose, tractor, woman, bus, shark, bicycle, bottle, lawn_mower, beetle, spider, skunk, seal, telephone, chair, lobster, lamp, worm, shrew, sunflower, butterfly, keyboard, baby, girl, orchid, bear, apple, orange