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_0887)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 887 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4118 |
| Val Accuracy | 0.3720 |
| Test Accuracy | 0.3896 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
house, lizard, skyscraper, forest, ray, train, squirrel, bed, sunflower, chair, television, man, crab, road, rabbit, possum, oak_tree, bus, trout, bear, tractor, beetle, bridge, fox, can, raccoon, cloud, porcupine, whale, worm, bee, butterfly, keyboard, sweet_pepper, bottle, sea, lion, apple, maple_tree, crocodile, skunk, motorcycle, chimpanzee, baby, mountain, cup, otter, poppy, dolphin, mouse