Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions

The task of semantic segmentation is to obtain strong pixel-level annotations for each pixel in the image. For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel-level annotations. However, the pixel-level annotation process is very expensive and...

Full description

Saved in:
Bibliographic Details
Main Authors: Xinying Xu, Guiqing Li, Gang Xie, Jinchang Ren, Xinlin Xie
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2019/9180391
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849413240228937728
author Xinying Xu
Guiqing Li
Gang Xie
Jinchang Ren
Xinlin Xie
author_facet Xinying Xu
Guiqing Li
Gang Xie
Jinchang Ren
Xinlin Xie
author_sort Xinying Xu
collection DOAJ
description The task of semantic segmentation is to obtain strong pixel-level annotations for each pixel in the image. For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel-level annotations. However, the pixel-level annotation process is very expensive and time-consuming. To reduce the cost, the paper proposes a semantic candidate regions trained extreme learning machine (ELM) method with image-level labels to achieve pixel-level labels mapping. In this work, the paper casts the pixel mapping problem into a candidate region semantic inference problem. Specifically, after segmenting each image into a set of superpixels, superpixels are automatically combined to achieve segmentation of candidate region according to the number of image-level labels. Semantic inference of candidate regions is realized based on the relationship and neighborhood rough set associated with semantic labels. Finally, the paper trains the ELM using the candidate regions of the inferred labels to classify the test candidate regions. The experiment is verified on the MSRC dataset and PASCAL VOC 2012, which are popularly used in semantic segmentation. The experimental results show that the proposed method outperforms several state-of-the-art approaches for deep semantic segmentation.
format Article
id doaj-art-6d1c5f2f32cc4bad9eba3fb837bb1a3f
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-6d1c5f2f32cc4bad9eba3fb837bb1a3f2025-08-20T03:34:10ZengWileyComplexity1076-27871099-05262019-01-01201910.1155/2019/91803919180391Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate RegionsXinying Xu0Guiqing Li1Gang Xie2Jinchang Ren3Xinlin Xie4College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, ChinaThe task of semantic segmentation is to obtain strong pixel-level annotations for each pixel in the image. For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel-level annotations. However, the pixel-level annotation process is very expensive and time-consuming. To reduce the cost, the paper proposes a semantic candidate regions trained extreme learning machine (ELM) method with image-level labels to achieve pixel-level labels mapping. In this work, the paper casts the pixel mapping problem into a candidate region semantic inference problem. Specifically, after segmenting each image into a set of superpixels, superpixels are automatically combined to achieve segmentation of candidate region according to the number of image-level labels. Semantic inference of candidate regions is realized based on the relationship and neighborhood rough set associated with semantic labels. Finally, the paper trains the ELM using the candidate regions of the inferred labels to classify the test candidate regions. The experiment is verified on the MSRC dataset and PASCAL VOC 2012, which are popularly used in semantic segmentation. The experimental results show that the proposed method outperforms several state-of-the-art approaches for deep semantic segmentation.http://dx.doi.org/10.1155/2019/9180391
spellingShingle Xinying Xu
Guiqing Li
Gang Xie
Jinchang Ren
Xinlin Xie
Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
Complexity
title Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
title_full Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
title_fullStr Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
title_full_unstemmed Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
title_short Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions
title_sort weakly supervised deep semantic segmentation using cnn and elm with semantic candidate regions
url http://dx.doi.org/10.1155/2019/9180391
work_keys_str_mv AT xinyingxu weaklysuperviseddeepsemanticsegmentationusingcnnandelmwithsemanticcandidateregions
AT guiqingli weaklysuperviseddeepsemanticsegmentationusingcnnandelmwithsemanticcandidateregions
AT gangxie weaklysuperviseddeepsemanticsegmentationusingcnnandelmwithsemanticcandidateregions
AT jinchangren weaklysuperviseddeepsemanticsegmentationusingcnnandelmwithsemanticcandidateregions
AT xinlinxie weaklysuperviseddeepsemanticsegmentationusingcnnandelmwithsemanticcandidateregions