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_0600)
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 | val |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | linear |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.01 |
| Seed | 600 |
| Random Crop | True |
| Random Flip | False |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9634 |
| Val Accuracy | 0.8952 |
| Test Accuracy | 0.8850 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
mouse, maple_tree, sweet_pepper, train, butterfly, skyscraper, chimpanzee, otter, shark, house, turtle, bear, raccoon, sea, chair, man, dinosaur, pickup_truck, cockroach, crocodile, cup, tank, snake, wardrobe, streetcar, motorcycle, beetle, bottle, pear, rabbit, palm_tree, plain, poppy, can, crab, beaver, oak_tree, lizard, bicycle, kangaroo, squirrel, fox, flatfish, bed, worm, cattle, rocket, road, skunk, pine_tree