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_0348)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.005 |
| Seed | 348 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9802 |
| Val Accuracy | 0.8963 |
| Test Accuracy | 0.8982 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
forest, sea, dinosaur, clock, couch, cup, worm, pickup_truck, porcupine, can, lamp, train, bridge, bottle, spider, whale, oak_tree, aquarium_fish, orange, flatfish, pear, tank, crab, elephant, beetle, cloud, rabbit, orchid, raccoon, willow_tree, lion, squirrel, mountain, apple, possum, woman, tulip, road, turtle, motorcycle, cattle, plate, trout, butterfly, fox, skyscraper, pine_tree, otter, mouse, bed