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_0854)
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 | 7e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 854 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9611 |
| Val Accuracy | 0.8659 |
| Test Accuracy | 0.8698 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
tank, crocodile, sunflower, pear, shark, house, camel, woman, wardrobe, porcupine, cattle, tractor, bee, maple_tree, table, rabbit, snail, boy, bicycle, dinosaur, butterfly, skyscraper, bus, raccoon, cloud, cockroach, beaver, kangaroo, lamp, bridge, orange, possum, forest, television, wolf, crab, trout, mushroom, train, leopard, streetcar, bottle, man, bowl, caterpillar, dolphin, rose, squirrel, lion, apple