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

facebooktwittermailshare

LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES

Abstract: 

Semantic segmentation of indoor scene images has a wide range of
applications. However, due to a large number of classes and uneven
distribution in indoor scenes, mislabels are often made when facing
small objects or boundary regions. Technically, contextual infor-
mation may benefit for segmentation results, but has not yet been
exploited sufficiently. In this paper, we propose a learnable contex-
tual regularization model for enhancing the semantic segmentation
results of color indoor scene images. This regularization model is
combined with a deep convolutional segmentation network without
significantly increasing the number of additional parameters. Our
model, derived from the inherent contextual regularization on the
indoor scene objects, benefits much from the learnable constrain-
t layers bridging the lower layers and the higher layers in the deep
convolutional network. The constraint layers are further integrated
with a weighted L1-norm based contextual regularization between
the neighboring pixels of RGB values to improve the segmenta-
tion results. Experimental results on NYUDv2 indoor scene dataset
demonstrate the effectiveness and efficiency of the proposed method.

up
0 users have voted:

Paper Details

Authors:
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan
Submitted On:
15 September 2017 - 7:33am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Xu Xiao
Paper Code:
1953
Document Year:
2017
Cite

Document Files

LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES

(168 downloads)

Subscribe

[1] Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan , "LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2122. Accessed: Jun. 18, 2018.
@article{2122-17,
url = {http://sigport.org/2122},
author = {Jun Chu ; Xu Xiao; Gaofeng Meng ; Lingfeng Wang and Chunhong Pan },
publisher = {IEEE SigPort},
title = {LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES},
year = {2017} }
TY - EJOUR
T1 - LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES
AU - Jun Chu ; Xu Xiao; Gaofeng Meng ; Lingfeng Wang and Chunhong Pan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2122
ER -
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan . (2017). LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES. IEEE SigPort. http://sigport.org/2122
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan , 2017. LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES. Available at: http://sigport.org/2122.
Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan . (2017). "LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES." Web.
1. Jun Chu , Xu Xiao, Gaofeng Meng , Lingfeng Wang and Chunhong Pan . LEARNABLE CONTEXTUAL REGULARIZATION FOR SEMANTIC SEGMENTATION OF INDOOR SCENE IMAGES [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2122