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_0752)
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 | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 752 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.3944 |
| Val Accuracy | 0.3437 |
| Test Accuracy | 0.3576 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
woman, lamp, turtle, bee, snail, kangaroo, caterpillar, possum, cockroach, television, mountain, lawn_mower, streetcar, sea, sunflower, apple, tiger, wolf, house, snake, tulip, lobster, maple_tree, bottle, shrew, mouse, plate, palm_tree, pine_tree, motorcycle, raccoon, cattle, fox, couch, poppy, bus, porcupine, boy, castle, baby, cloud, camel, pickup_truck, beaver, lion, oak_tree, willow_tree, dolphin, rabbit, crocodile