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_0767)
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 | cosine_with_restarts |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 767 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9985 |
| Val Accuracy | 0.8976 |
| Test Accuracy | 0.9030 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
raccoon, ray, plate, man, bowl, skyscraper, beaver, pear, turtle, orchid, porcupine, clock, sunflower, wolf, chair, sweet_pepper, caterpillar, possum, woman, dolphin, tractor, rocket, willow_tree, apple, forest, lizard, orange, lobster, mountain, snail, chimpanzee, skunk, kangaroo, motorcycle, mushroom, cattle, worm, trout, bridge, squirrel, bus, house, can, pine_tree, mouse, keyboard, rose, fox, lamp, wardrobe