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_0773)
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 | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 773 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9490 |
| Val Accuracy | 0.5984 |
| Test Accuracy | 0.6096 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
plain, porcupine, fox, plate, poppy, crocodile, sea, couch, rose, bicycle, cockroach, beaver, trout, worm, television, apple, shark, can, wardrobe, ray, tulip, possum, table, hamster, butterfly, leopard, skyscraper, bowl, pear, skunk, crab, caterpillar, lamp, cattle, bridge, shrew, bear, dinosaur, tank, castle, forest, dolphin, motorcycle, chair, flatfish, orchid, wolf, palm_tree, sweet_pepper, keyboard