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_0712)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 712 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4559 |
| Val Accuracy | 0.4112 |
| Test Accuracy | 0.4126 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, bottle, road, chimpanzee, bowl, lion, fox, plate, palm_tree, chair, whale, crocodile, wolf, bus, tiger, woman, couch, motorcycle, bicycle, rose, house, wardrobe, leopard, raccoon, tulip, hamster, otter, orchid, pickup_truck, cup, cockroach, aquarium_fish, sunflower, mouse, forest, seal, rabbit, lobster, lizard, dinosaur, can, shrew, train, skyscraper, possum, skunk, table, tractor, orange, baby