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_0912)
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 | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 912 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9977 |
| Val Accuracy | 0.9080 |
| Test Accuracy | 0.9168 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, oak_tree, plain, train, television, turtle, porcupine, tank, fox, lizard, cockroach, telephone, crocodile, man, kangaroo, flatfish, pine_tree, snake, squirrel, motorcycle, bridge, caterpillar, bear, lamp, bus, clock, castle, trout, keyboard, leopard, palm_tree, lawn_mower, orchid, sea, dinosaur, rocket, rose, worm, willow_tree, poppy, chimpanzee, chair, skyscraper, elephant, skunk, wolf, seal, bottle, beetle, road