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_0246)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 246 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9489 |
| Val Accuracy | 0.8693 |
| Test Accuracy | 0.8738 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, boy, mushroom, tulip, wardrobe, house, baby, bee, dolphin, possum, couch, mouse, mountain, road, porcupine, cockroach, raccoon, flatfish, crocodile, seal, bridge, rocket, bowl, bottle, beetle, lion, ray, train, keyboard, otter, orchid, shrew, wolf, pickup_truck, pine_tree, crab, fox, rose, apple, sea, pear, snail, lamp, rabbit, camel, motorcycle, whale, bicycle, castle, poppy