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_0888)
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 | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 888 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9806 |
| Val Accuracy | 0.8917 |
| Test Accuracy | 0.8954 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
aquarium_fish, whale, man, cloud, bee, squirrel, otter, telephone, plate, dolphin, pear, sea, woman, rabbit, bowl, girl, skunk, forest, motorcycle, trout, crocodile, rocket, keyboard, butterfly, wardrobe, lobster, possum, camel, mountain, lion, pickup_truck, lawn_mower, seal, plain, beaver, turtle, spider, tractor, rose, bottle, streetcar, raccoon, castle, bed, chimpanzee, television, sweet_pepper, hamster, porcupine, palm_tree