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_0276)
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 | 0.0003 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.05 |
| Seed | 276 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6918 |
| Val Accuracy | 0.5373 |
| Test Accuracy | 0.5370 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
dolphin, crab, pear, bowl, dinosaur, plate, bear, possum, leopard, porcupine, butterfly, forest, man, sea, hamster, bee, woman, orchid, orange, plain, worm, apple, table, kangaroo, mountain, couch, rose, boy, maple_tree, snail, oak_tree, cup, streetcar, lawn_mower, wardrobe, lizard, clock, tiger, trout, bridge, pickup_truck, camel, cloud, road, keyboard, cattle, shark, sweet_pepper, house, mouse