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_0592)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 592 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9834 |
| Val Accuracy | 0.8968 |
| Test Accuracy | 0.8866 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
hamster, chair, lobster, sunflower, crocodile, mushroom, possum, orange, bicycle, wolf, cattle, lamp, tractor, rabbit, willow_tree, snail, poppy, spider, mountain, telephone, boy, rose, baby, lion, butterfly, tulip, trout, table, orchid, cup, forest, crab, bus, pear, man, keyboard, plate, elephant, palm_tree, house, porcupine, bed, wardrobe, squirrel, cloud, otter, sea, train, shark, clock