No description, website, or topics provided.
Switch branches/tags
Nothing to show
Clone or download
Latest commit 05dee37 Dec 6, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
figs add figs Oct 17, 2018
models add instancenorm Sep 5, 2018
utils first commit Sep 5, 2018
.gitignore ignore checkpoints Sep 5, 2018
LICENSE Create LICENSE Sep 5, 2018
README.md Update README.md Dec 6, 2018
main.py dafult options Sep 5, 2018

README.md

Batch-Instance-Normalization

This repository provides an example of using Batch-Instance Normalization (NIPS 2018) for classification on CIFAR-10/100, written by Hyeonseob Nam and Hyo-Eun Kim at Lunit Inc.

Acknowledgement: This code is based on Wei Yang's pytorch-classification

Citation

If you use this code for your research, please cite:

@inproceedings{nam2018batch,
  title={Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks},
  author={Nam, Hyeonseob and Kim, Hyo-Eun},
  booktitle={Advances in Neural Information Processing Systems},
  year={2018}
}

Prerequisites

Training Examples

Training ResNet-50 on CIFAR-100 using Batch Normalization

python main.py --dataset cifar100 --depth 50 --norm bn --checkpoint checkpoints/cifar100-resnet50-bn

Training ResNet-50 on CIFAR-100 using Instance Normalization

python main.py --dataset cifar100 --depth 50 --norm in --checkpoint checkpoints/cifar100-resnet50-in

Training ResNet-50 on CIFAR-100 using Batch-Instance Normalization

python main.py --dataset cifar100 --depth 50 --norm bin --checkpoint checkpoints/cifar100-resnet50-bin

Summary of Results

  1. Classification on CIFAR-10/100 (ResNet-110) and ImageNet (ResNet-18)

  1. Classification on CIFAR-100 with different architectures

  1. Mixed-domain classification on Office-Home (ResNet-18)

  1. Character recognition on ICDAR2003, ICDAR2005, and Chars74K

Links