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_0500)
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 | constant |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 500 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8760 |
| Val Accuracy | 0.5299 |
| Test Accuracy | 0.5286 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
cockroach, streetcar, palm_tree, bicycle, whale, raccoon, beaver, lizard, tulip, maple_tree, otter, cattle, castle, boy, skunk, plain, sweet_pepper, butterfly, aquarium_fish, cloud, motorcycle, bee, beetle, porcupine, snail, shark, mouse, squirrel, tank, orchid, leopard, keyboard, chimpanzee, seal, mountain, woman, kangaroo, television, bowl, road, lamp, chair, lawn_mower, dinosaur, elephant, wolf, plate, trout, lion, baby