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_0878)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 878 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9462 |
| Val Accuracy | 0.8635 |
| Test Accuracy | 0.8670 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, worm, lion, caterpillar, cup, pickup_truck, bus, house, tiger, lamp, beetle, fox, girl, dinosaur, possum, woman, bottle, bear, rose, apple, boy, camel, hamster, orchid, dolphin, keyboard, elephant, sweet_pepper, tank, baby, otter, table, bed, snail, tractor, skunk, castle, willow_tree, rocket, lizard, sunflower, forest, mountain, can, chimpanzee, trout, whale, raccoon, road, maple_tree