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_0188)
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 | cosine |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 188 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9227 |
| Val Accuracy | 0.8627 |
| Test Accuracy | 0.8604 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, telephone, bridge, boy, can, beetle, caterpillar, apple, aquarium_fish, mountain, bus, woman, girl, turtle, mouse, skunk, sunflower, shark, tulip, pear, lobster, tank, poppy, tractor, cup, pine_tree, flatfish, lamp, bowl, oak_tree, porcupine, television, plate, dinosaur, trout, seal, leopard, hamster, castle, whale, keyboard, rabbit, tiger, pickup_truck, wardrobe, worm, house, snake, crocodile, chair