Awesome

MoEx (Moment Exchange)

The official PyTorch implementation of the paper On Feature Normalization and Data Augmentation.

CVPR 2021

Authors:

• Boyi Li*
• Felix Wu*
• Ser-Nam Lim
• Serge Belongie
• Kilian Q. Weinberger

*: Equal Contribution

Overview

This repo contains the PyTorch implementation of Moment Exchange (MoEx), described in the paper On Feature Normalization and Data Augmentation. For ImageNet and CIFAR experiments, we select Positional Normalization (PONO) as the feature normalization method.

Usage

Please follow the instructions in the README.md in each subfolder to run experiments with MoEx on CIFAR, ImageNet, and ModelNet10/40.

Explorations beyond our paper

Methods for COVID‐19

• A Cascade‐SEME network for COVID‐19 detection in chest c‐ray images: Paper

More information and relevant applications will be updated.

If you find this repo useful, please cite:

@inproceedings{li2021feature,
  title={On feature normalization and data augmentation},
  author={Li, Boyi and Wu, Felix and Lim, Ser-Nam and Belongie, Serge and Weinberger, Kilian Q},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={12383--12392},
  year={2021}
}

@inproceedings{li2019positional,
  title={Positional Normalization},
  author={Li, Boyi and Wu, Felix and Weinberger, Kilian Q and Belongie, Serge},
  booktitle={Advances in Neural Information Processing Systems},
  pages={1620--1632},
  year={2019}
}