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_0225)
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 | 0.0001 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 225 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9511 |
| Val Accuracy | 0.8771 |
| Test Accuracy | 0.8778 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
wardrobe, palm_tree, mouse, tractor, rose, flatfish, beetle, seal, motorcycle, wolf, elephant, trout, castle, can, dinosaur, butterfly, cattle, sweet_pepper, bee, road, mushroom, lobster, beaver, couch, whale, aquarium_fish, otter, train, spider, poppy, porcupine, lion, oak_tree, kangaroo, cup, cloud, snake, skunk, rabbit, bus, sea, telephone, rocket, pear, raccoon, baby, orange, ray, orchid, lamp