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_0724)
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 | 0.0003 |
| LR Scheduler | linear |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 724 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9864 |
| Val Accuracy | 0.8237 |
| Test Accuracy | 0.8180 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tulip, train, leopard, beetle, hamster, table, pine_tree, sweet_pepper, oak_tree, castle, bowl, whale, tank, man, beaver, otter, road, skyscraper, tiger, lamp, mushroom, wolf, boy, dolphin, pear, shark, flatfish, aquarium_fish, chair, rose, sea, bottle, seal, cattle, television, lobster, worm, girl, rocket, couch, turtle, spider, wardrobe, bed, poppy, streetcar, orange, kangaroo, camel, sunflower