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_0646)
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_with_restarts |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 646 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.5219 |
| Val Accuracy | 0.4352 |
| Test Accuracy | 0.4342 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shark, trout, fox, sweet_pepper, cockroach, wardrobe, bowl, bus, bicycle, lawn_mower, television, kangaroo, tiger, chimpanzee, cattle, orange, plate, raccoon, girl, lizard, sea, pear, poppy, man, hamster, motorcycle, bee, cup, orchid, crocodile, chair, skyscraper, mouse, mountain, pickup_truck, beaver, tank, bed, flatfish, castle, possum, rocket, house, caterpillar, train, streetcar, telephone, clock, butterfly, squirrel