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_0329)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 329 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9624 |
| Val Accuracy | 0.8664 |
| Test Accuracy | 0.8662 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
motorcycle, house, bowl, hamster, tulip, bicycle, cloud, fox, television, wolf, mountain, chair, flatfish, turtle, maple_tree, pear, lobster, bed, cup, cockroach, spider, bridge, dinosaur, bus, crocodile, road, kangaroo, porcupine, tiger, baby, apple, poppy, squirrel, tractor, pickup_truck, lion, shrew, dolphin, willow_tree, orchid, can, lamp, skyscraper, lizard, pine_tree, snake, chimpanzee, possum, rose, wardrobe