Distribution Padding in Convolutional Neural Networks

Anh Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)


Even though zero padding is usually a staple in convolutional neural networks to maintain the output size, it is highly suspicious because it significantly alters the input distribution around border region. To mitigate this problem, in this paper, we propose a new padding technique termed as distribution padding. The goal of the method is to approximately maintain the statistics of the input border regions. We introduce two different ways to achieve our goal. In both approaches, the padded values are derived from the means of the border patches, but those values are handled in a different way in each variant. Through extensive experiments on image classification and style transfer using different architectures, we demonstrate that the proposed padding technique consistently outperforms the default zero padding, and hence can be a potential candidate for its replacement.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781538662496
Publication statusPublished - 2019 Sept
Event26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
Duration: 2019 Sept 222019 Sept 25

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Conference26th IEEE International Conference on Image Processing, ICIP 2019
Country/TerritoryTaiwan, Province of China

Bibliographical note

Funding Information:
This work was supported by Samsung Research Funding Center of Samsung Electronics under Project Number SRFC-IT1702-08.

Publisher Copyright:
© 2019 IEEE.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'Distribution Padding in Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this