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_0158)
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 | 9e-05 |
| LR Scheduler | constant |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 158 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9426 |
| Val Accuracy | 0.8499 |
| Test Accuracy | 0.8470 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
beetle, butterfly, shrew, bee, mountain, maple_tree, fox, leopard, bear, rose, orange, woman, can, cloud, hamster, tank, pine_tree, plate, mouse, porcupine, lamp, possum, man, clock, cattle, elephant, bed, chimpanzee, bicycle, caterpillar, shark, cup, lizard, wolf, table, bottle, palm_tree, snail, bridge, oak_tree, squirrel, sunflower, spider, seal, chair, willow_tree, bus, couch, baby, apple