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_0053)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 53 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9895 |
| Val Accuracy | 0.8883 |
| Test Accuracy | 0.8910 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
keyboard, forest, chair, mushroom, clock, shrew, palm_tree, spider, skyscraper, possum, tulip, beetle, trout, bridge, pickup_truck, leopard, road, bowl, table, caterpillar, motorcycle, rabbit, turtle, tiger, couch, seal, mountain, lizard, wardrobe, butterfly, castle, orange, lawn_mower, dolphin, telephone, ray, snake, porcupine, tank, man, beaver, bear, tractor, snail, wolf, rose, woman, pear, worm, shark