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_0060)
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 | 5e-05 |
| LR Scheduler | cosine |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 60 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9840 |
| Val Accuracy | 0.9003 |
| Test Accuracy | 0.8934 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dinosaur, clock, keyboard, poppy, girl, camel, trout, spider, kangaroo, castle, woman, rocket, squirrel, orchid, bottle, hamster, bee, turtle, house, bus, lizard, mushroom, elephant, streetcar, plate, willow_tree, pickup_truck, leopard, cattle, table, sea, raccoon, baby, mouse, cloud, bowl, snail, snake, apple, telephone, dolphin, bear, caterpillar, road, sunflower, rabbit, skyscraper, chimpanzee, skunk, shrew