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_0781)
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 | 9e-05 |
| LR Scheduler | constant_with_warmup |
| Epochs | 6 |
| Max Train Steps | 1998 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 781 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9876 |
| Val Accuracy | 0.8477 |
| Test Accuracy | 0.8556 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mushroom, can, motorcycle, flatfish, skunk, sea, whale, possum, fox, spider, dolphin, baby, bowl, hamster, castle, couch, telephone, crocodile, cattle, shrew, clock, aquarium_fish, lion, snake, squirrel, willow_tree, butterfly, wardrobe, plain, cup, train, road, otter, turtle, bridge, house, girl, bicycle, television, bear, pear, keyboard, palm_tree, shark, crab, streetcar, seal, boy, oak_tree, orange