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_0267)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | linear |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 267 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9593 |
| Val Accuracy | 0.6301 |
| Test Accuracy | 0.6254 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, streetcar, chair, cloud, tiger, raccoon, lizard, caterpillar, television, tractor, lamp, road, maple_tree, rose, bowl, kangaroo, beetle, cockroach, telephone, willow_tree, house, turtle, bed, shark, lawn_mower, snake, bicycle, table, tulip, cup, sweet_pepper, bridge, spider, pine_tree, ray, mountain, plain, woman, rocket, tank, chimpanzee, forest, orange, man, hamster, fox, squirrel, wolf, bus, bear