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_0142)
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 | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 142 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9946 |
| Val Accuracy | 0.8941 |
| Test Accuracy | 0.9000 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, castle, cattle, girl, lion, crab, lawn_mower, bottle, train, orchid, seal, beetle, spider, chair, dolphin, ray, man, poppy, plain, oak_tree, hamster, cloud, bridge, tiger, bus, lobster, cup, motorcycle, cockroach, lamp, apple, camel, sunflower, table, whale, fox, flatfish, sweet_pepper, rocket, orange, willow_tree, mushroom, mouse, shark, bowl, wolf, worm, tractor, house, road