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_0023)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0003 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 23 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9479 |
| Val Accuracy | 0.8416 |
| Test Accuracy | 0.8308 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, wardrobe, wolf, house, snail, crab, plate, seal, skyscraper, cloud, ray, worm, lobster, beaver, lamp, streetcar, bear, shark, maple_tree, orchid, mouse, tractor, bowl, turtle, table, chair, orange, motorcycle, elephant, porcupine, fox, cockroach, butterfly, skunk, bee, hamster, crocodile, sea, mushroom, willow_tree, apple, oak_tree, castle, rabbit, pickup_truck, snake, tiger, shrew, train, rocket