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_0571)
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 | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 571 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9596 |
| Val Accuracy | 0.8651 |
| Test Accuracy | 0.8652 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, apple, shrew, mountain, worm, telephone, ray, bed, bear, trout, seal, tractor, dolphin, flatfish, rocket, tiger, can, oak_tree, raccoon, keyboard, pear, wardrobe, elephant, cup, orchid, train, beetle, snake, porcupine, rabbit, leopard, boy, lizard, motorcycle, lobster, hamster, bowl, tulip, bridge, bus, baby, road, shark, forest, plate, possum, plain, orange, television, bee