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_0224)
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 | 0.0001 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 8 |
| Max Train Steps | 2664 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 224 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9935 |
| Val Accuracy | 0.9048 |
| Test Accuracy | 0.8942 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
table, television, trout, butterfly, sunflower, kangaroo, woman, aquarium_fish, elephant, spider, dolphin, skyscraper, lizard, cloud, maple_tree, house, can, pickup_truck, beetle, lawn_mower, crab, poppy, orange, fox, cattle, pear, streetcar, shrew, possum, caterpillar, motorcycle, forest, skunk, turtle, hamster, willow_tree, bowl, tractor, orchid, whale, camel, seal, dinosaur, tulip, sea, couch, bed, crocodile, beaver, snail