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_0034)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 34 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9952 |
| Val Accuracy | 0.8776 |
| Test Accuracy | 0.8656 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sweet_pepper, elephant, snail, tiger, can, cloud, bottle, sea, woman, oak_tree, crocodile, seal, bicycle, cup, raccoon, bus, tractor, forest, otter, fox, bear, aquarium_fish, snake, wardrobe, bowl, plain, palm_tree, butterfly, cattle, flatfish, man, porcupine, orchid, pine_tree, lamp, plate, lawn_mower, wolf, chair, keyboard, pickup_truck, poppy, lion, table, kangaroo, skunk, dinosaur, maple_tree, lobster, mouse