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_0855)
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 | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0001 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 855 |
| Random Crop | False |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9555 |
| Val Accuracy | 0.8592 |
| Test Accuracy | 0.8440 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pine_tree, lion, skunk, bee, bridge, man, orange, sweet_pepper, wolf, ray, lawn_mower, rocket, bed, tulip, chimpanzee, castle, crocodile, cup, sunflower, lizard, possum, mushroom, plain, dolphin, otter, skyscraper, orchid, willow_tree, couch, camel, rose, bus, worm, girl, palm_tree, mountain, streetcar, crab, rabbit, tank, elephant, pickup_truck, road, tiger, raccoon, maple_tree, spider, bowl, chair, cockroach