Learning semantic segmentation score in weakly supervised convolutional neural network

Fariz Ikhwantri, Novian Habibie, Arie Rachmad Syulistyo, Aprinaldi, Wisnu Jatmiko

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

1 Citation (Scopus)

Abstract

Semantic segmentation is an image labeling process for each pixels according to defined objects class and its presence in an image. Labeling process consists of recognizing, detecting location and labeling pixels that defines the object in the image. Annotation result of semantic segmentation needs ground truth to verify accuracy of score prediction. Therefore, this research propose a model to predict score of annotation accuracy. By casting the problem into constraining object boundary recognition, we described the annotation using foreground mask. To extract the feature, we used convolution neural network. We only used CNN trained on a image level annotation. In order to be able to infer the pixel instance, we adapt CNN architecture into weakly supervised learning. Experiments were conducted by finetuning Convolution Neural Network for object recognition using weakly supervised architecture for multilabel classification. In this paper we proposed to score semantic segmentation based on bag level information without the availability of pixel level annotation.

Original languageEnglish
Title of host publicationProceedings - 2015 International Conference on Computers, Communications and Systems, ICCCS 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages19-25
Number of pages7
ISBN (Electronic)9781467397568
DOIs
Publication statusPublished - 7 Sep 2016
Event2015 International Conference on Computers, Communications and Systems, ICCCS 2015 - Kanyakumari, India
Duration: 2 Nov 20153 Nov 2015

Publication series

NameProceedings - 2015 International Conference on Computers, Communications and Systems, ICCCS 2015

Conference

Conference2015 International Conference on Computers, Communications and Systems, ICCCS 2015
CountryIndia
CityKanyakumari
Period2/11/153/11/15

Keywords

  • Convolutional Neural Networks
  • Jaccard Index
  • Multiple Instance Learning
  • Regression
  • Semantic Segmentation
  • Weakly Supervised Learning

Fingerprint Dive into the research topics of 'Learning semantic segmentation score in weakly supervised convolutional neural network'. Together they form a unique fingerprint.

  • Cite this

    Ikhwantri, F., Habibie, N., Syulistyo, A. R., Aprinaldi, & Jatmiko, W. (2016). Learning semantic segmentation score in weakly supervised convolutional neural network. In Proceedings - 2015 International Conference on Computers, Communications and Systems, ICCCS 2015 (pp. 19-25). [7562845] (Proceedings - 2015 International Conference on Computers, Communications and Systems, ICCCS 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCOMS.2015.7562845