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_0475)
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 | 5e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 5 |
| Max Train Steps | 1665 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 475 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9957 |
| Val Accuracy | 0.9053 |
| Test Accuracy | 0.9084 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
rose, orange, oak_tree, possum, dolphin, mountain, rocket, lobster, lamp, snail, beetle, man, trout, streetcar, keyboard, sea, castle, palm_tree, snake, hamster, raccoon, pickup_truck, couch, butterfly, clock, mouse, flatfish, spider, turtle, bicycle, caterpillar, cloud, girl, sweet_pepper, pear, bear, worm, cup, aquarium_fish, lion, cattle, lawn_mower, tank, dinosaur, train, table, cockroach, squirrel, baby, television