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_0689)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 689 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9961 |
| Val Accuracy | 0.9195 |
| Test Accuracy | 0.9196 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
camel, lobster, crab, shrew, worm, skyscraper, tank, shark, elephant, lion, television, turtle, bicycle, seal, skunk, cup, hamster, mushroom, streetcar, train, orange, willow_tree, chimpanzee, plain, apple, trout, keyboard, rose, poppy, cattle, woman, kangaroo, lawn_mower, lamp, porcupine, telephone, orchid, tractor, dinosaur, bus, lizard, mouse, tiger, can, fox, pear, beetle, spider, plate, aquarium_fish