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_0778)
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 | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 778 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9764 |
| Val Accuracy | 0.5459 |
| Test Accuracy | 0.5780 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
orange, crab, telephone, caterpillar, poppy, beaver, bus, dinosaur, rose, can, turtle, palm_tree, tiger, raccoon, cloud, keyboard, snake, whale, bridge, mushroom, spider, man, road, tulip, boy, lawn_mower, bed, flatfish, streetcar, forest, fox, beetle, leopard, apple, possum, cockroach, shark, castle, porcupine, squirrel, aquarium_fish, bottle, willow_tree, house, elephant, baby, lobster, tractor, sea, pear