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_0287)
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 | 3e-05 |
| LR Scheduler | cosine_with_restarts |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 287 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.8617 |
| Val Accuracy | 0.7973 |
| Test Accuracy | 0.8072 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
couch, television, skunk, seal, apple, tiger, dolphin, road, butterfly, mountain, boy, ray, castle, squirrel, rose, train, man, beetle, can, woman, cockroach, bicycle, lizard, camel, whale, turtle, pine_tree, plate, keyboard, dinosaur, chimpanzee, kangaroo, lion, palm_tree, possum, leopard, girl, skyscraper, spider, lobster, table, bridge, poppy, bed, bowl, shrew, rabbit, snake, elephant, rocket