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_0898)
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 | constant |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 898 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9840 |
| Val Accuracy | 0.8416 |
| Test Accuracy | 0.8474 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, hamster, dinosaur, wardrobe, castle, pine_tree, oak_tree, tulip, skyscraper, house, worm, boy, plate, clock, snake, skunk, flatfish, cockroach, raccoon, maple_tree, rose, possum, spider, beaver, tank, rabbit, chair, willow_tree, cup, squirrel, poppy, caterpillar, mouse, lamp, telephone, aquarium_fish, wolf, train, chimpanzee, cloud, motorcycle, cattle, crab, can, orange, porcupine, man, bee, elephant, lizard