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_0818)
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 |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 818 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9641 |
| Val Accuracy | 0.8856 |
| Test Accuracy | 0.8682 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, house, squirrel, lawn_mower, ray, raccoon, telephone, cup, boy, apple, porcupine, bear, sunflower, plate, fox, snake, orange, pickup_truck, cockroach, seal, lizard, maple_tree, skyscraper, bus, keyboard, bee, poppy, forest, rocket, tiger, couch, elephant, camel, orchid, hamster, palm_tree, mushroom, bed, willow_tree, otter, turtle, dolphin, bottle, oak_tree, rabbit, butterfly, cattle, wolf, rose, sea