Skip to main navigation Skip to search Skip to main content

Iterative weakly supervised semantic segmentation network with fused superpixel clues

  • Wu Xiaoning*
  • , Li Ruixin
  • , Zhu Xinli
  • , Zhu Siyan
  • , Cui Daowang
  • *Corresponding author for this work
  • North Automatic Control Technology Institute

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Most weakly supervised semantic segmentation networks lack semantic information between pixels, resulting in incomplete segmentation of targets. In this paper, we propose an iterative weakly supervised semantic segmentation network with fused superpixel clues. First, we generate attention class activation maps from the intermediate layers of the classification network, then use superpixel clues to optimize the class attention region and generate pseudo-labels with pixel correlations. After training the semantic segmentation network on these pseudo-labels, we continue to input the predicted pixel map iteratively into the superpixel network and the semantic segmentation network until the entire process is complete and the final semantic segmentation map is obtained. Results on PASCAL VOC 2012 demonstrate that the proposed method has superior segmentation performance compared with other weakly supervised semantic segmentation methods.

Original languageEnglish
Title of host publicationICNC-FSKD 2023 - 2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
EditorsLiang Zhao, Guanglu Sun, Kenli Li, Zheng Xiao, Lipo Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350304398
DOIs
StatePublished - 2023
Externally publishedYes
Event19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2023 - Harbin, China
Duration: 29 Jul 202331 Jul 2023

Publication series

NameICNC-FSKD 2023 - 2023 19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

Conference

Conference19th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2023
Country/TerritoryChina
CityHarbin
Period29/07/2331/07/23

Keywords

  • Deep convolutional neural networks
  • Image-level labels
  • Superpixel
  • Weakly-supervised semantic segmentation

Fingerprint

Dive into the research topics of 'Iterative weakly supervised semantic segmentation network with fused superpixel clues'. Together they form a unique fingerprint.

Cite this