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_0703)
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 | constant |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 703 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9540 |
| Val Accuracy | 0.8547 |
| Test Accuracy | 0.8452 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rabbit, dinosaur, wolf, pine_tree, tiger, bed, dolphin, mushroom, boy, worm, sunflower, cattle, butterfly, chair, sweet_pepper, forest, couch, oak_tree, possum, castle, plate, trout, spider, tractor, streetcar, table, house, beetle, woman, snail, otter, road, maple_tree, beaver, orchid, whale, turtle, bicycle, raccoon, lizard, clock, willow_tree, elephant, plain, poppy, crocodile, man, keyboard, bottle, shark