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_0300)
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 | cosine |
| Epochs | 9 |
| Max Train Steps | 2997 |
| Batch Size | 64 |
| Weight Decay | 0.007 |
| Seed | 300 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9999 |
| Val Accuracy | 0.8704 |
| Test Accuracy | 0.8710 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
worm, crab, bicycle, ray, camel, skunk, motorcycle, rabbit, possum, beetle, trout, road, chimpanzee, whale, cattle, boy, pickup_truck, woman, cup, clock, plate, tiger, table, lizard, elephant, porcupine, bridge, skyscraper, leopard, spider, palm_tree, bus, wardrobe, wolf, bottle, shark, train, poppy, dinosaur, bowl, orchid, sunflower, willow_tree, raccoon, mouse, keyboard, rocket, flatfish, forest, lion