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_0732)
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 | constant_with_warmup |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 732 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9444 |
| Val Accuracy | 0.8499 |
| Test Accuracy | 0.8460 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lobster, spider, wolf, bowl, oak_tree, lion, tank, turtle, dolphin, rabbit, shrew, streetcar, possum, rose, beetle, willow_tree, shark, chimpanzee, lawn_mower, pickup_truck, sweet_pepper, orange, telephone, mountain, rocket, tulip, keyboard, caterpillar, butterfly, cloud, mouse, bed, boy, mushroom, table, lizard, otter, leopard, dinosaur, orchid, train, elephant, sunflower, raccoon, squirrel, skunk, maple_tree, trout, man, camel