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_0283)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 283 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9538 |
| Val Accuracy | 0.8419 |
| Test Accuracy | 0.8508 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, house, castle, aquarium_fish, girl, streetcar, lawn_mower, worm, tulip, woman, table, caterpillar, telephone, kangaroo, butterfly, snake, dinosaur, mushroom, seal, raccoon, lizard, clock, mountain, porcupine, otter, trout, bed, fox, chimpanzee, plate, road, crocodile, motorcycle, elephant, snail, bridge, squirrel, man, train, possum, poppy, shark, tractor, bear, sea, rocket, cup, orange, shrew, lobster