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_0963)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 963 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9949 |
| Val Accuracy | 0.8776 |
| Test Accuracy | 0.8830 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
lion, boy, turtle, house, dolphin, whale, ray, sunflower, tulip, chair, wardrobe, dinosaur, plain, bus, plate, skunk, orange, castle, pear, elephant, pine_tree, butterfly, motorcycle, seal, caterpillar, cockroach, baby, cattle, crocodile, hamster, can, beetle, bridge, maple_tree, raccoon, skyscraper, streetcar, rocket, shark, tiger, leopard, lamp, possum, fox, lawn_mower, spider, otter, wolf, chimpanzee, aquarium_fish