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_0426)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 426 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9923 |
| Val Accuracy | 0.8963 |
| Test Accuracy | 0.8890 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, bridge, cup, castle, porcupine, otter, bus, woman, sweet_pepper, squirrel, can, trout, dolphin, orchid, seal, possum, streetcar, mouse, man, road, ray, maple_tree, willow_tree, table, baby, orange, cockroach, skunk, oak_tree, rose, crocodile, bear, tank, kangaroo, tractor, elephant, plate, crab, butterfly, train, snake, fox, keyboard, sunflower, apple, leopard, beaver, motorcycle, house, plain