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_0961)
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 | constant |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 961 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9763 |
| Val Accuracy | 0.8589 |
| Test Accuracy | 0.8596 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
skunk, palm_tree, wardrobe, bridge, telephone, sea, baby, lamp, sunflower, seal, dinosaur, kangaroo, pickup_truck, cockroach, poppy, cup, rocket, man, motorcycle, possum, hamster, chimpanzee, skyscraper, willow_tree, television, rabbit, fox, raccoon, keyboard, lion, elephant, sweet_pepper, cattle, bee, camel, bed, dolphin, mouse, maple_tree, mountain, turtle, spider, porcupine, cloud, train, woman, pear, house, rose, squirrel