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_0553)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 553 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7870 |
| Val Accuracy | 0.5376 |
| Test Accuracy | 0.5320 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, bee, poppy, cup, camel, crab, can, clock, castle, willow_tree, shrew, aquarium_fish, tulip, plate, streetcar, tiger, snake, bed, table, dinosaur, chair, butterfly, mouse, lizard, house, lawn_mower, lamp, keyboard, orange, skyscraper, beetle, fox, tank, road, oak_tree, forest, turtle, hamster, flatfish, possum, elephant, plain, snail, otter, cattle, whale, crocodile, lobster, porcupine, sweet_pepper