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_0290)
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 | 0.0001 |
| LR Scheduler | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 290 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9816 |
| Val Accuracy | 0.8424 |
| Test Accuracy | 0.8554 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, fox, butterfly, orchid, crocodile, rose, porcupine, orange, tiger, girl, beaver, squirrel, palm_tree, lobster, tulip, worm, snake, plate, possum, bee, train, telephone, rocket, sea, pine_tree, cloud, lamp, boy, oak_tree, plain, television, pear, bottle, cup, dinosaur, whale, streetcar, bicycle, willow_tree, baby, caterpillar, forest, skunk, dolphin, leopard, hamster, flatfish, spider, table, pickup_truck