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_0777)
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 | 7e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 777 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9241 |
| Val Accuracy | 0.8587 |
| Test Accuracy | 0.8554 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
trout, turtle, tiger, bear, house, shark, boy, caterpillar, couch, tank, sweet_pepper, cup, girl, snake, plate, worm, man, lamp, keyboard, raccoon, whale, bicycle, pine_tree, orange, rabbit, wolf, dinosaur, seal, bowl, streetcar, rocket, apple, table, beaver, otter, clock, tulip, motorcycle, kangaroo, telephone, hamster, elephant, mountain, road, bee, baby, bus, dolphin, train, cockroach