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_0285)
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 | constant_with_warmup |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 285 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6965 |
| Val Accuracy | 0.5307 |
| Test Accuracy | 0.5592 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
can, castle, wardrobe, skyscraper, telephone, maple_tree, dinosaur, lobster, mouse, lamp, shark, wolf, flatfish, television, cockroach, sea, train, bottle, sweet_pepper, apple, orange, ray, bear, caterpillar, otter, palm_tree, leopard, camel, table, crocodile, shrew, rocket, worm, bowl, house, dolphin, chimpanzee, couch, skunk, bus, lizard, keyboard, tractor, whale, hamster, road, pine_tree, snail, possum, lion