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_0879)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 879 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9676 |
| Val Accuracy | 0.8589 |
| Test Accuracy | 0.8552 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
sunflower, plain, streetcar, house, girl, baby, mountain, crocodile, mouse, aquarium_fish, skunk, crab, keyboard, pine_tree, palm_tree, can, bicycle, lion, cloud, rose, leopard, bowl, seal, boy, sweet_pepper, caterpillar, ray, beaver, bottle, clock, bus, otter, telephone, bee, road, woman, apple, spider, lobster, mushroom, willow_tree, turtle, pickup_truck, beetle, cockroach, train, tiger, plate, cup, maple_tree