By Senwei Liang*, Zhongzhan Huang* (* contribute equally), Mingfu Liang and Haizhao Yang.

This repository is the implementation of "Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise" [paper] on CIFAR-100 dataset.

Instance Enhancement Batch Normalization (IEBN) is an attention-based version of BN which recalibrates channel information of BN by a simple linear transformation.

• Python 3.6 and PyTorch 1.0

python cifar.py -a iebn_resnet --dataset cifar100 --block-name bottleneck --depth 164 --epochs 164 --schedule 81 122 --gamma 0.1 --wd 1e-4 --checkpoint checkpoints/cifar100/resnet-164-iebn

Notes:

• Training on 2 GPUs

Many thanks to bearpaw for his simple and clean Pytorch framework for image classification task.