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_0363)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 7e-05 |
| LR Scheduler | cosine |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 363 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9732 |
| Val Accuracy | 0.8803 |
| Test Accuracy | 0.8800 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
oak_tree, rabbit, flatfish, road, porcupine, tractor, lobster, bottle, lion, bus, streetcar, cloud, crab, spider, bear, beaver, ray, bridge, clock, tulip, shrew, house, palm_tree, skyscraper, keyboard, telephone, plain, turtle, orchid, aquarium_fish, pine_tree, mushroom, pear, leopard, elephant, girl, bicycle, cattle, mouse, seal, whale, snail, mountain, willow_tree, possum, skunk, dinosaur, orange, crocodile, castle