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_0795)
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 | linear |
| Epochs | 7 |
| Max Train Steps | 2331 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 795 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9201 |
| Val Accuracy | 0.5835 |
| Test Accuracy | 0.5804 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bottle, girl, oak_tree, rocket, train, spider, cockroach, whale, elephant, hamster, castle, pine_tree, bee, caterpillar, crab, mouse, porcupine, clock, tulip, leopard, palm_tree, chimpanzee, tank, seal, maple_tree, flatfish, wardrobe, woman, pickup_truck, orchid, butterfly, dinosaur, willow_tree, chair, kangaroo, boy, beaver, mushroom, lizard, aquarium_fish, snake, skunk, sunflower, rabbit, rose, crocodile, keyboard, snail, shark, forest