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_0540)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 540 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9585 |
| Val Accuracy | 0.8592 |
| Test Accuracy | 0.8716 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, boy, pickup_truck, house, cup, girl, motorcycle, bridge, shark, trout, beaver, orange, mountain, sweet_pepper, television, bed, shrew, spider, bear, lamp, seal, castle, sunflower, cattle, fox, bee, woman, caterpillar, ray, porcupine, lawn_mower, plain, leopard, apple, train, bowl, pear, snake, flatfish, squirrel, wardrobe, aquarium_fish, dolphin, tulip, tractor, crab, rose, oak_tree, tiger, otter