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_0419)
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 | 0.0005 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 419 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4045 |
| Val Accuracy | 0.3608 |
| Test Accuracy | 0.3556 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
palm_tree, whale, possum, lizard, woman, bridge, rose, wardrobe, caterpillar, beaver, worm, fox, plate, camel, orange, seal, skunk, rocket, forest, bear, crab, willow_tree, lawn_mower, chair, television, otter, baby, maple_tree, can, crocodile, castle, sweet_pepper, clock, mushroom, bowl, beetle, bottle, telephone, pear, hamster, train, turtle, sunflower, spider, dinosaur, girl, bee, porcupine, boy, keyboard