Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS

Abstract: 

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.

up
0 users have voted:

Paper Details

Authors:
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee
Submitted On:
17 September 2019 - 3:06am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Duc Nguyen
Paper Code:
ICIP-2737
Document Year:
2019
Cite

Document Files

distributional padding.pptx

(10)

Subscribe

[1] Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee, "DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS ", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4654. Accessed: Oct. 20, 2019.
@article{4654-19,
url = {http://sigport.org/4654},
author = {Anh-Duc Nguyen; Seonghwa Choi; Woojae Kim; Sewoong Ahn; Jinwoo Kim; Sanghoon Lee },
publisher = {IEEE SigPort},
title = {DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS },
year = {2019} }
TY - EJOUR
T1 - DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS
AU - Anh-Duc Nguyen; Seonghwa Choi; Woojae Kim; Sewoong Ahn; Jinwoo Kim; Sanghoon Lee
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4654
ER -
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee. (2019). DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS . IEEE SigPort. http://sigport.org/4654
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee, 2019. DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS . Available at: http://sigport.org/4654.
Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee. (2019). "DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS ." Web.
1. Anh-Duc Nguyen, Seonghwa Choi, Woojae Kim, Sewoong Ahn, Jinwoo Kim, Sanghoon Lee. DISTRIBUTION PADDING IN CONVOLUTIONAL NEURAL NETWORKS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4654