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_0434)
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 | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 434 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9832 |
| Val Accuracy | 0.8083 |
| Test Accuracy | 0.8092 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
snail, sweet_pepper, train, skunk, television, cockroach, shrew, whale, plain, pear, tulip, tractor, keyboard, palm_tree, fox, plate, butterfly, worm, seal, leopard, bear, lobster, wolf, motorcycle, possum, can, rabbit, otter, orchid, bicycle, camel, spider, maple_tree, bowl, oak_tree, wardrobe, streetcar, castle, beaver, chimpanzee, man, poppy, rocket, bed, bridge, orange, boy, aquarium_fish, forest, crab