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_0973)
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 | 0.0005 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 973 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6757 |
| Val Accuracy | 0.4739 |
| Test Accuracy | 0.4712 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
chair, leopard, snail, tank, forest, caterpillar, beetle, butterfly, lobster, wolf, tiger, apple, possum, shark, spider, oak_tree, lizard, train, man, couch, cockroach, mountain, lawn_mower, rabbit, castle, sunflower, maple_tree, crab, hamster, aquarium_fish, shrew, bridge, tractor, pine_tree, boy, seal, bottle, bowl, dinosaur, dolphin, porcupine, telephone, squirrel, otter, turtle, chimpanzee, plate, rose, lion, bus