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_0007)
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 | cosine |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 7 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9288 |
| Val Accuracy | 0.6112 |
| Test Accuracy | 0.5978 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snake, keyboard, butterfly, fox, lizard, orchid, house, rabbit, plain, ray, dolphin, castle, bus, woman, shrew, rocket, turtle, plate, bridge, sunflower, leopard, bottle, porcupine, streetcar, beetle, trout, tractor, possum, cup, skyscraper, skunk, pickup_truck, dinosaur, chair, cattle, lobster, aquarium_fish, seal, mushroom, pear, oak_tree, baby, crocodile, lamp, crab, lion, bear, spider, pine_tree, wardrobe