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_0874)
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 | 3e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 874 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9710 |
| Val Accuracy | 0.8816 |
| Test Accuracy | 0.8834 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, raccoon, plain, lizard, oak_tree, chair, bed, lamp, snake, road, mushroom, whale, table, leopard, seal, can, lawn_mower, kangaroo, rocket, train, bear, plate, beetle, tractor, castle, baby, fox, poppy, man, bridge, palm_tree, lion, chimpanzee, wolf, willow_tree, camel, spider, cockroach, dinosaur, skyscraper, house, pickup_truck, telephone, bowl, dolphin, bus, tulip, butterfly, orange, shark