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_0304)
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 | 0.0005 |
| LR Scheduler | linear |
| Epochs | 2 |
| Max Train Steps | 666 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 304 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.6142 |
| Val Accuracy | 0.5227 |
| Test Accuracy | 0.5350 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
squirrel, spider, tulip, crab, shrew, bee, bed, can, whale, sunflower, turtle, rose, couch, ray, pickup_truck, cup, cloud, clock, poppy, camel, orange, lamp, oak_tree, lizard, bus, bridge, lobster, motorcycle, dinosaur, mouse, snail, trout, girl, tank, tiger, chimpanzee, pear, fox, baby, bicycle, crocodile, chair, plate, beetle, pine_tree, wardrobe, plain, road, table, flatfish