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_0800)
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 | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 800 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.7418 |
| Val Accuracy | 0.7112 |
| Test Accuracy | 0.7130 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
train, clock, plate, boy, man, otter, chair, dinosaur, sea, keyboard, cloud, maple_tree, lamp, seal, pine_tree, forest, butterfly, hamster, road, dolphin, bottle, tractor, bee, sunflower, streetcar, table, possum, chimpanzee, beaver, porcupine, mountain, mushroom, girl, worm, whale, skyscraper, wardrobe, aquarium_fish, flatfish, fox, tiger, squirrel, rocket, bed, willow_tree, can, orange, bicycle, mouse, sweet_pepper