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_0448)
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 | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 448 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9920 |
| Val Accuracy | 0.8851 |
| Test Accuracy | 0.8812 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
television, elephant, bowl, ray, can, leopard, whale, streetcar, bear, tiger, baby, orange, turtle, train, telephone, aquarium_fish, kangaroo, camel, bottle, man, spider, fox, cloud, cockroach, butterfly, mouse, sunflower, woman, lizard, mountain, pickup_truck, rose, squirrel, mushroom, caterpillar, table, raccoon, flatfish, pear, lamp, girl, possum, dolphin, bus, castle, plate, otter, lawn_mower, chimpanzee, bridge